Why: .pre-commit-hooks.yaml and its release-tag gate served external
consumers that do not exist. No repo on the Gitea instance pins these
hooks, and the README names apm as the only supported install path. The
mechanism was also already failing: skill-size-check.sh changed after
v2.0.1 with no tag cut, and the gate cannot fire through Gitea's merge
button. (Simplification audit finding 36.)
Implementation Notes:
- Delete .pre-commit-hooks.yaml, scripts/check-release-needed.sh,
tests/test-check-release-needed.sh and tests/test-vale-hooks-consumer.sh,
and remove the check-release-needed pre-push hook. The repo: local
skill-size-check and vale-audit-prefilter-* hooks are unchanged.
- ADR-0014 is amended, not retired: its runtime decision to bundle Vale
inside factory-audit stands. The amendment keeps the entry[0]-only
constraint (LESSONS.md:101,105) in case the export returns. ADR-0025
gets a pointer.
- test-vale-wrap.sh: drop case 33 (the cross-manifest drift check) and
case 28's hook-scope half, which read the published manifest. Case 32
now also requires each hook to select every tracked file of its class,
which keeps case 33's one-plugin-narrowing guard, with a mutation test.
- test-skill-size-check.sh and test-adr0020-contract.sh now assert the
hook contract and verbose: true on .pre-commit-config.yaml only.
- gates.md: pre-push count goes from 9 to 8 authored hooks (11 to 10
reported), and the Release table, the External consumers section and
the two-manifest scope table are removed. README and script/test
comments no longer describe the export as live. The resolver comment
is edited identically in both copies.
- The v1.0.0/v2.0.0/v2.0.1 tags are left in place; they are inert.
ADR: 0014
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Why: two branches that both bump a skill 1.0.0 -> 1.0.1 with different
content merge without a conflict, and each passed the gate against its own
merge-base, so main could ship two changes under one version.
Implementation Notes:
- check-skill-version-bump requires the pushed version to exceed both the
merge-base and the main tip; failures name the baseline they missed.
- Presence is read from the tree, so a blob missing from a partial clone is
a read failure instead of a silently exempt "new" skill.
- A leading UTF-8 BOM no longer reads as a missing version.
- Version parts reject leading zeros in all three validators
(check-skill-version-bump, skill-size-check, factory-audit).
- New tests cover equal bumps, moved files, major/minor ordering, bad refs,
unreadable blobs, mode-only changes, symlinks and tag peeling.
Impact: ADR-0022 amended (reverses "not main's current tip"); gates.md
updated to match, including pre-commit 4.6.1's exact ref selection.
ADR: 0022
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
ADR-0022 and gates.md now state the merge-base baseline, the fail-closed
cases, the PyYAML requirement and the multi-ref push gap (shared with
check-release-needed); the new hook gets its own gates.md group. Both
ADR additions follow each file's amendment format. README and AGENTS.md
now say to discard a refreshed apm.lock.yaml on a feature branch, and
that an .apm/ edit is live only once it is on the remote's main.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
check-skill-version-bump fails a push when a skill directory changed
against its merge-base with main (tests/ excluded) without a strictly
higher metadata.version than main. New, renamed and deleted skills are
exempt; every plugin is covered. Recorded as a dated section in
ADR-0022 and documented in gates.md.
Patch-bumps the 17 skills that changed on this branch without a bump,
so the branch passes its own gate. Simplification audit finding 33.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Why
A six-agent review of the two preceding commits found their code sound -- the
differential claim holds, the published hook contract is byte-unchanged -- but
their prose drifted from it in three ways: statements of fact the code
contradicts, markers in a convention this repo does not use, and figures that
went stale when the merge changed what they counted.
Implementation Notes
ADR-0025's edge-path table is rewritten around one stated doctrine: exit 0 is
audited and clean, exit 1 is audited with findings or a target present but
unreadable, exit 2 is that nothing was audited. Its old row 1 promised "one
generic matches-neither message" for three different inputs; there are three
distinct messages, and the missing-path case exited 1 until the preceding commit
fixed it. Rows are added for the preflight and CDPATH changes, because a table
claiming to enumerate every entry-point behaviour change reproduces its own
"an earlier revision of this ADR said they were behaviour-neutral" failure if it
omits any.
ADR-0025 also gains a Consequences supersession record in ADR-0016's form:
partially-superseded entries for 0008, 0014, 0020 and 0021, and explicit
"is not superseded" entries with reasoning for the rest. Twelve ADRs are amended
and it previously listed none.
ADR-0008 moves from an amendment note to partially superseded. Its contract
genuinely narrowed -- an agent .md outside an agents/ directory was audited
before the merge and is refused now -- and ADR-0020 already recorded that the
merge "reopens ADR-0008". Its detector description said "a path under
.apm/agents/", the phrasing ADR-0025 rejects as wider than the script and
circular; the shipped rule is a .md whose immediate parent is named agents/, at
any scope.
ADR-0020's amendment claimed the boundary resolver is sourced by
validate-provenance.sh. It is not, and never was; only validate.sh sources it,
once per mode branch. Three Home-column entries pointed at reference filenames
the merge renamed, one of which now resolves to two files because its row covers
skills and agents.
Five ADRs opened with "Skill renamed per ADR-0025", a form this repo does not
use, in the same commit that used the conventional "Amended by ADR-0025" twice.
They are normalized. "Renamed" was also wrong: the BREAKING-CHANGE trailer says
the skills were removed and their flows merged.
SIMPLIFICATION-AUDIT.md had 2026-09-15 notes attached to headlines that were
never updated, against its own convention of correcting in place with
strikethrough. Every figure here was re-derived at HEAD by command, and several
differed from the review's own numbers, so the notes record the basis rather
than the result alone.
LESSONS.md asserted the two review-time suite failures were the SIGPIPE race.
The commit that fixed that race explicitly declined to claim it -- the suite was
running while agents edited live config files -- so the hedge is restored.
Impact
No code, test or configuration change; documentation only. Suites stay 20/20
strict with 0 skipped and 374/374 bats. No gate parses ADR or gates.md content,
so nothing here is load-bearing for a hook.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YR2CjVumUbEGWcMikcoXBD
Why
Two suites failed intermittently — tests/test-vale-wrap.sh case 21 and
tests/test-check-release-needed.sh cases 4 and 15 — on correct output, and never
when run alone. The cause is the `echo "$OUT" | grep -q P` idiom under
`set -o pipefail`: grep -q exits as soon as it has an answer, bash's echo can
hand a multi-line value to the pipe one line at a time, and a write after the
reader is gone kills echo with SIGPIPE. pipefail then reports the writer's
death, so output that DID match reads as "no match". Every observed failure had
lines after its match; case 15's match is on line 1 of 6, the widest window in
that file.
Forced with a pause before the writer's last line, the pipe form failed 50 of 50
runs; a here-string, a match on the last line, and the same pipe without
pipefail each passed 50 of 50. Unforced the rate is about 1 per 670 suite runs,
which is why it read as a flaky gate rather than a bug.
The failures at review time are consistent with this, but were not proven to be
it: the suite was running while agents edited live config files in place, and a
brief change to .vale.ini or .pre-commit-hooks.yaml would produce the same two
failures. The race is real and fixed either way.
Implementation Notes
`grep -q P <<< "$VAR"` has no separate writer process, so there is nothing to
race. It is not a retry or a sleep. 121 sites converted across 9 files, three of
them scripts rather than tests: new-agent.sh, new-skill.sh and
check-executables-allow-sync.sh. None ships via .pre-commit-hooks.yaml, so no
external consumer pins them, and all three are single-pipeline checks whose
verdict cannot change.
Left alone deliberately: 14 sites whose writer is a command, not a shell
builtin — they either absorb the writer's status with `|| true` or are python3
and awk, which write once at exit — and one file with no pipefail. `printf '%s'`
sites differ from a here-string only by a trailing newline, which no -q verdict
on a non-empty pattern depends on.
tests/test-no-pipefail-early-exit-grep.sh is a static guard against new
occurrences, discovered automatically by run-tests.sh. It only scans files that
set pipefail, joins continuation lines, skips comments, and flags only
echo/printf writers. Its first case proves the scanner can fail before its
second trusts a clean verdict on the tree.
A guard covers exactly the spellings its regex models, so the miss surface was
measured rather than assumed. Four were found and closed: pipefail declared as
`set -o errexit -o pipefail` (where the old pattern required pipefail to follow
the FIRST -o, and a file-level miss skips every site in that file); a writer
separated from grep by an intermediate stage; a pipeline wrapped on a trailing
`|` rather than a backslash; and readers spelled egrep, fgrep, /bin/grep,
`command grep` or with an env-var prefix. Segment characters exclude a bare `&`
so `echo ok && other | grep -q x`, whose writer is `other`, does not false-fire.
Widening surfaced 5 live sites invisible to the original scanner, all in
tests/test-apm-current-hook.sh, all `echo "$out" | json_field ... | grep -q`;
they are safe today only because json_field is python3, which reads to EOF and
writes once. Fixtures go 4 to 12 vulnerable spellings plus near-miss negatives.
Two `grep ... | head -1` sites (test-vale-wrap.sh) are the same race with a
different early-exiting reader, and are fixed by absorbing the writer. The
scanner deliberately does not model `head`, `sed -n 1p` or a bare `read`: most
legitimate uses in this tree are already absorbed with `|| true` and the scanner
cannot see absorption from pipeline text, so a high false-positive rate would be
how this guard gets weakened. Heredoc bodies are scanned as code; none in the
tree trips it today.
Impact
The bug predates the factory-audit merge: every converted site in
check-release-needed and case 21 dates to 4d018af and aa8cc22 (2026-08-09).
Test suites go 19 to 20. `run-tests.sh --strict` passes 20/20 with 0 skipped,
four consecutive runs.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YR2CjVumUbEGWcMikcoXBD
Why
The two audit skills carried 1,724 lines of byte-identical duplication: the ADR-0020 boundary
resolver (1,061), vale-wrap.sh (526), the Vale style rules (44) and the Contributing-files parser
(93). Nothing shared them — they were held in sync by a 413-line pre-push gate and its 797-line
test suite. Sync-by-gate had already failed once: at 484357a the two parser copies drifted into
different spellings of the bullet loop while a docstring asserted they were identical. That drift
was behaviour-neutral and was re-unified by hand at 598a7c3, so the copies were identical at merge
time — but nothing had caught it, and the next drift need not be neutral.
Implementation Notes
Self-containment binds BETWEEN skills, not within one. The agentskills.io spec forbids reaching
across skill directories, which is why two separate skills needed embedded copies; two files inside
ONE skill may source a third. That is the whole reason the merge removes duplication rather than
relocating it.
The union of both bodies measured 1,532 words against BODY_MAX_WORDS=900, and only 211 of those
words were shared, so SKILL.md is a dispatch body. Step 0 resolves the flow from the target path
before any validation, and its table mirrors validate.sh's detection exactly: a directory holding
SKILL.md or a SKILL.md file (skill); a *.agent.md, or a .md directly under an agents/ directory
(agent); anything else stops without running a validator. Steps 1-3 live in
references/skill-flow.md and references/agent-flow.md, and gotchas that apply to one flow live in
that flow's file, since it is loaded on every invocation anyway. If validate.sh reports on the
other artifact type, the body restarts at Step 0.
Named factory-audit rather than forge-audit because forge is a live skill, and a family prefix that
matches a live sibling reads as ownership rather than membership.
The description carries one arrow per boundary target, because ADR-0020 resolves only the first
target after an arrow. It drops the quoted "audit this skill"-style phrases, which restated
"audited" in a second register (ADR-0020's duplicate-register rule). 241 characters, Gotchas 16%
of the body: no size SUGGESTIONs.
The boundary resolver stays embedded in two files rather than imported: a cache-installed plugin
cannot read outside its own directory, and the repo-root hook resolves via .pre-commit-hooks.yaml
where entry[0] is the only token pre-commit rewrites, so no single file is reachable by both.
tests/test-adr0020-contract.sh hashes both copies for byte-identity, and asserts validate.sh sources
the resolver and that no third copy exists.
The entry scripts classify the target from its resolved parent directory, so a bare agent filename
typed inside agents/ works; resolve SCRIPT_DIR CDPATH-safely; and exit 2 when a lib-*.sh is
missing, rather than dying with exit 1, the tier the flows relay as real findings.
The provenance run functions stash their findings code in KYBERFORGE_PROV_RC and
return 0, so validate-provenance.sh calls them UNTESTED. Testing a function's
status (`f || RC=$?`) disables errexit for its entire body, and no subshell or
`set -e` inside can re-arm it once the call sits in a condition context
(measured, both spellings). Their error paths use `exit`, which is unaffected
either way; this keeps errexit armed for anything added later.
Case 0's readability guard reads the file instead of asking `[[ -r ]]`. `-r` is
access(2), which answers yes for uid 0 even on a mode-000 file, and this repo's
dev environment is root -- so the guard could never fire where it exists to fire.
A read attempt is also the stricter question, catching EIO. This is the reasoning
scripts/check-vale-style-sync.sh carried before this commit deleted it; the
hazard did not go with it.
All three entry scripts are CDPATH-safe, vale-wrap.sh included: both of its cd sites are cleared,
the --config resolution and the directory-mirror walk, where an exported CDPATH would otherwise
print a decoy path into the -print0 stream and build the mirror from the decoy's files. The two
remaining bare cd calls take absolute paths, which CDPATH is never consulted for.
Impact
BREAKING: skill-audit and agent-audit no longer exist as invocable skills. kyberforge goes to
2.0.0 (catalog 0.4.7).
Check logic is unchanged: differential runs of the old and new validators across every skill and
agent produced byte-identical stdout, stderr and exit codes, and the reconstructed Python payloads
differ only in comments and the references/field-inventory.md -> agent-field-inventory.md rename.
One doctrine governs the tiers: exit 0 is audited and clean, exit 1 is audited with findings OR a
target present but unreadable, exit 2 is that nothing was audited at all. Edge paths DID change,
deliberately (full table in ADR-0025):
- a missing target exits 2 (never ran), not 1, under its own "does not exist" message; detection is
by path shape, so a shape-matching path that is simply absent used to reach the validator and come
back as a FAIL against a file that never existed;
- an unshaped target exits 2 under the generic "matches neither" message, and a directory with no
SKILL.md under a third, distinct one -- three exit-2 messages, not one;
- a dangling symlink or a symlink loop stays exit 1: it is present but broken, which is a finding
about the artifact rather than a usage error;
- a SKILL.md file path is audited as its skill directory instead of refused;
- a .md agent outside an agents/ directory is refused rather than audited;
- a missing script library, a missing python3, a missing PyYAML, and no argument at all each exit 2.
validate-provenance.sh already exited 2 for the last two; validate.sh now matches it.
.pre-commit-hooks.yaml is a published contract consumed by external repos. Both hook IDs and both
files: regexes are unchanged; only entry: and description: moved.
scripts/check-vale-style-sync.sh (413), scripts/sync-vale-styles.sh (21),
tests/test-check-vale-style-sync.sh (797) and agent-audit/scripts/README.md (47) are deleted. The
checker made 17 assertions: 6 compared the two Vale copies and are moot; 10 are rehomed into
tests/test-vale-wrap.sh (case 0, cases 28-31, and the suite's Vale-absent skip); and the
cross-manifest files: agreement check, which selected hooks by entry: and so could not survive both
hooks sharing one, is ported as case 33 pairing hooks by id:. Cases 28, 30 and 33 carry mutation
self-tests; narrowing the local skill prefilter to 6 of 38 SKILL.md files now fails the suite.
Skills go 39 to 38. Pre-push goes 9 repo-authored hooks to 8.
ADR: 0025
BREAKING-CHANGE: the skill-audit and agent-audit skills are removed. Both flows are served by
factory-audit, which auto-detects whether it was handed a skill directory or an agent file.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YR2CjVumUbEGWcMikcoXBD
A five-agent review of today's seven commits found no executable
regressions and no dangling references, but a set of documents still
asserting, in present tense, machinery that ADR-0024 and its commits
removed. This corrects them in place, keeping the original text as the
historical record wherever the repo's amendment convention applies.
LESSONS.md: the 2026-06-21 entry prescribed a `claude plugin validate`
sweep that now fails on every plugin, so it is marked superseded with
the surviving gates named. The 2026-08-09 entry gained a recurrence
note: today's manifest deletion broke apm's MCP propagation exactly as
that lesson describes, and its prescribed repo-local grep could not
have caught it, because `plugin_parser.py` ships in the apm toolchain
installed outside this repository.
ADR-0019, ADR-0011 and ADR-0021: amendments extended to passages the
earlier correction passes stepped over -- a dead native-consumer guard,
Consequences bullets still calling for a `plugins/gitea/.mcp.json` that
must not be recreated, and a drift-gate list naming a deleted script.
ADR-0021's list is down to one gate, not two: `apm audit --ci` never
read `description` and was never a drift gate.
architecture.md and enrichments.md: the self-containment constraint is
restated on its live source, the agentskills.io APM package-mode spec,
rather than on Claude Code's plugin cache-install, which ADR-0024
consequence 6 pins as a superseded rationale. releasing.md's pointer to
the deleted sync script is rewritten as history.
tests/run-bats.sh and scripts/lib/batch-run.sh: comment-only. The
`.claude/skills/` exclusion comment claimed a duplication that is not
live yet; apm does not strip `tests/`, and the deployed tree is empty
of them only because the lockfile still resolves the six dependencies
to a pre-ADR-0024 commit carrying the flat mirror. The exclusion is
correct but forward-looking, and now says so.
SIMPLIFICATION-AUDIT.md: reconciled against what the commits actually
did. Two closed findings recorded conclusions that ADR-0024 reversed
hours later; findings 1, 3, 31 and 35 carried prescriptions voided the
same day; finding 28 is now recorded as having moved backwards, with
docs/adr/ measured at +336 lines over the day. The section 1 headline
table is re-measured at a6434e0 and labelled with its basis. The
ADR-0012 contradiction between finding 2b and section 8 is resolved in
2b's favour after reading the ADR: only finding 24 is governed by it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YR2CjVumUbEGWcMikcoXBD
718c79a deleted every per-plugin .claude-plugin/plugin.json, which
reclassified each package from a marketplace plugin to a plain apm
package. That silently broke MCP propagation: apm_cli/deps/plugin_parser.py
maps a plugin-root .mcp.json into .apm/.mcp.json, and that code path runs
only for marketplace plugins. With no manifest, apm never reads the file.
Reproduced on ref-pinned consumer clones: at the parent commit a consumer
receives the obsidian server, at HEAD it receives none, and on upgrade apm
prints "Removed stale MCP server 'obsidian' from .mcp.json". This repo
consumes its own plugins through apm (ADR-0018), so the tracked root
.mcp.json would have been rewritten to an empty server map on the next
lock re-resolve -- silent tool loss plus unexplained working-tree drift.
The server is removed entirely rather than relocated to .apm/. It was
already a standing question (SIMPLIFICATION-AUDIT finding 37, deferred on
2026-09-13 pending confirmation, now confirmed), and plugins/bin/apm.yml
declares dependencies.mcp: [] -- apm's supported mechanism was never used.
All seven .mcp.json files go; the root one is apm-generated output and is
now gitignored alongside the other install artifacts.
ADR-0011's deferred ".mcp.json wiring gap" is moot twice over -- the
install route it blocked no longer exists and neither does the file --
and ADR-0018 records why it lost its only worked example of MCP
propagation. apm.lock.yaml still carries the server; it clears on the
first apm update after this reaches the default branch.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YR2CjVumUbEGWcMikcoXBD
A five-agent review of 718c79a and d2480b8 found no skill, agent or hook
regressions (39 skills before and after) and confirmed both hook removals
are genuinely moot -- verified against the tree, not taken on the commit's
word. It did find one functional regression (fixed separately) and this
documentation drift.
Counting errors, all from a git pathspec `*` crossing `/`:
- 17 .bats files shipped to consumers is really 10; 17 counted tracked
paths merely containing /tests/, one of them a template asset
- "roughly 88s off every push" is ~92.4s; 88 omitted validate-plugins
- "roughly 70% of each plugin remains live" holds only for kyberforge;
the real spread is 44.3% (bin) to 70.6%, now a table
- the pre-push enforcement row was half-corrected: 33 entries stood
unstruck (now 27) and 14 -> 11 switched counting basis mid-sentence
- the root .claude-plugin/plugin.json was described as "kept"; it has
never been tracked
gates.md said "Ten hooks" above a nine-row table (11 was decremented for
one removal, not two), and "both need the claude CLI" for one remaining
validator. Its pretty-format-json exclude rationale claimed six
alternations expanding to sixteen files in a passage headed "Mind which
number you are quoting" -- four alternations, two live files; the two
dead ones are dropped from the pattern. check-useless-excludes could not
catch this: it only flags an exclude matching nothing at all.
ADR-0024 cited ADR-0006 for a patch-bump rule it does not contain and
which ADR-0015 explicitly retired; stated apm's marketplace probe order
backwards (.claude-plugin/ is the last candidate, not the first, so the
earlier .github/plugin/ deletion only demoted resolution); undercounted
apm's skill-deploying targets as seven when there are fifteen; and never
recorded that validate-plugins was removed. The symlink hedge is resolved:
apm_cli/security/gate.py's ignore_non_content() drops symlinks silently on
deploy while apm_modules/ materialization dereferences them, so content
survives that far and vanishes at install. Accepted with no replacement
guard, per decision -- kyberforge/docs/hooks.md previously asserted a
guard that had been deleted with its script.
Four plugin READMEs still advertised `claude plugin install`; ADRs 0001,
0006, 0013, 0014, 0015 and 0019 described deleted machinery in the present
tense, 0019 most consequentially as the live justification for the
SessionStart hook's .apm/ path. CONTEXT.md's "apm package" entry forbade
"plugin" while using it in its own body, and "Output profile" lost the
antecedent for "one catalogue serves both".
run-tests.sh gains the .claude/skills/ exclusion run-bats.sh already had.
Latent today -- no test-*.sh lives under any .apm/skills/*/tests/ -- but
apm now deploys those directories, so one would be discovered twice.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YR2CjVumUbEGWcMikcoXBD
apm becomes the only supported install path. The flat mirror at each plugin
root existed solely so Claude Code's native `claude plugin install` could
convention-scan plugin content (ADR-0017). With no native consumers, it cost
~20,000 tracked lines plus ~2,100 lines of sync tooling and ~88s of every
push to guard content apm never reads — and its only automated gate,
`claude plugin validate --strict`, passes on a plugin with zero content, so
it could not detect the defect ADR-0017 was created to fix.
Removes the mirror (213 files), the six per-plugin manifest pairs,
sync-plugin-content.sh, its 1,289-line test, the orphaned
marketplace-plugins.sh, and the check-plugin-content-sync and
validate-plugins pre-push hooks. The root `marketplace:` block and
.claude-plugin/ catalogue stay: apm's own marketplace consumers read that
same file, so `<name>@holocron` short names keep working.
tests/run-bats.sh now excludes .claude/skills/. apm installs from .apm/,
which carries the tests/ dirs the mirror stripped, so deployed .bats files
would otherwise be discovered and double-run.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YR2CjVumUbEGWcMikcoXBD
apm-marketplace-check checked network reachability of remote marketplace
refs, but finding 35 already removed the only remote package entry, so
every marketplace.packages[] source is local and the hook is pure
overlap with apm-pack-check-clean. apm-audit-ci was re-examined and kept
as-is -- its pre-commit-config.yaml comment already carries a dated,
verified justification the audit had missed.
check-marketplace-mirror-sync guarded .github/plugin/marketplace.json
against drift from .claude-plugin/marketplace.json. Verified against
current GitHub Copilot CLI docs: Copilot's marketplace discovery already
falls back through .github/plugin/marketplace.json to
.claude-plugin/marketplace.json, which this repo generates anyway -- the
dedicated mirror bought a discovery-order preference, not a capability.
Deleted the mirror file, its sync script, its test, and the hook.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YR2CjVumUbEGWcMikcoXBD
Neither has a real consumer: Codex is not a supported target, and
mattpocock-skills was the sole remote marketplace.packages[] entry
forcing apm-marketplace-check and apm-pack-check-clean to git
ls-remote on every push. Removing both drops .agents/plugins/marketplace.json
(the codex output artifact) and makes every pre-push hook resolve
fully offline. Updates README, AGENTS.md, gates.md, architecture.md,
and ADR-0015/ADR-0021 to match.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YR2CjVumUbEGWcMikcoXBD
Cut the "Verified fixed" reproduction paragraph carrying explicitly
stale pre-retrofit figures, and condensed the "Current retrofit
status" section's issue-#99 process narrative to the current-state
facts and the commands to check them.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YR2CjVumUbEGWcMikcoXBD
skill-frontmatter was a 62-line bash script inlined in
.pre-commit-config.yaml, re-parsing SKILL.md frontmatter with grep and
awk to check for name/description/metadata.version fields.
skill-size-check.sh already parses the same frontmatter block with
PyYAML for its ADR-0020 checks, so the two checks belonged in one
script.
Adds a ~20-line required-frontmatter check (name, description,
metadata.version as three-part semver) to scripts/skill-size-check.sh.
Removes the inline skill-frontmatter hook from .pre-commit-config.yaml
and deletes tests/test-skill-frontmatter.sh (366 lines). Removes the
79-line "the other hook on that scope" discussion from
docs/spec/gates.md and its now-dangling cross-reference, replacing
both with a one-line note of the fold, and updates the pre-push hook
counts there.
Updates fixture builders in test-skill-size-check.sh,
test-adr0020-body-checks.sh, test-adr0020-targets.sh,
test-adr0020-differential.sh, and test-vale-hooks-consumer.sh to carry
valid metadata.version so the new check doesn't spuriously fail
existing fixtures that predate it.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YR2CjVumUbEGWcMikcoXBD
Six pre-push hooks were validating overlapping sets of the same
manifests. check-manifests (marketplace.json/plugin.json path checks)
is redundant with validate-plugins (claude plugin validate) and
apm-pack-check-clean, which already cover the same ground.
Deletes the check-manifests hook entry, scripts/check-manifests.sh
(282 lines), and tests/test-check-manifests.sh (771 lines).
scripts/lib/marketplace-plugins.sh is kept — it is still sourced by
sync-plugin-content.sh. Updates the now-stale check-manifests.sh
mentions and hook counts in README.md and docs/spec/gates.md.
The apm-audit-ci and apm-marketplace-check hooks named in the same
finding are left untouched — the audit flags them as needing a
separate decision.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YR2CjVumUbEGWcMikcoXBD
Finding 21: `config.example.json` (and the never-tracked
`.claude/plugins/git/config.json` it documented) was read by
git-orchestrate and git-branches but written by nothing, and the
default-inference fallback (GitHub Flow, with Gitflow inferred from a
`develop`/`release/*` branch) already covered the no-config case.
Removed the config-read step from both, updated git-workflow's
description of the orchestrator to match, dropped the now-dangling
`applied_config` field from git-orchestrate's output shape, and
deleted the config file and its stale example reference in
docs/spec/architecture.md.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01YR2CjVumUbEGWcMikcoXBD
The #113 sweep rested on CLAUDE.md's premise that rtk either filters or passes through unchanged,
so prefixing is always safe. Measured against rtk 0.42.4, that premise is false for several of the
commands the sweep prefixed, and two skills were left giving wrong answers silently.
Why:
- `rtk git worktree list --porcelain -z` discards both flags and renders its own format. The
`locked`/`lock_reason` fields git-worktrees Step 2 must emit are absent entirely, and paths under
$HOME are abbreviated to `~/`.
- `rtk git branch --list <name>` prints a phantom `* ` line even when nothing matches, so
git-branches' stated ambiguity test — "output from both means the name is ambiguous" — reported
every name as ambiguous. `tag --list` is a clean passthrough, so only one half broke.
- `rtk git diff --name-only`/`--name-status` append a `Changes:` trailer to output documented as
"one per line"; `--word-diff` emits none of the `[-removed-] {+added+}` markers its table
describes; `rtk git log -L` truncates each line at ~72 chars, on the one command whose purpose is
showing line content.
- `rtk git stash pop` prints only `FAILED: git stash pop`, swallowing the conflict diagnostic and
retained-entry message the surrounding prose tells the agent to rely on.
Implementation notes:
- Eleven sites reverted to bare `git`, each carrying its reason inline so the next sweep does not
undo it. `mergetool` and `rebase -i` are reverted on clause 3's interactive limb only: the TTY
defect does not reproduce — rtk filters exactly twelve subcommands and execs the rest — and
ADR-0023 records that measurement rather than a convenient one.
- ADR-0023 states the rule repo-wide with a third clause: a command whose output the skill parses,
or which is interactive, stays bare. `plugins/git/README.md` is reduced to a pointer; its claim
that gitea skills "contain no git/rtk mentions at all" was false, and its citation of
`hard-rules.md` pointed at a file containing no occurrence of "rtk".
- Eight gitea sites swept, all verified byte-identical passthroughs first.
- `scripts/check-rtk-prefix.sh` gates clause 1. Run against main's pre-sweep corpus it reports 99
findings including every gitea site, so it would have caught the drift #113 was filed about.
Impact: the gate covers clause 1 only, in shell-tagged fences and the opening span of Run cells.
Clause 2 is not gateable — "Run `git switch`" and "`git switch` refuses" are the same tokens — and
prose bullets are invisible to it. Both limits are recorded in gates.md rather than left implied.
Refs: #113
ADR: 0023
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EeH8SCbcrCAQrtymkNuhKP
The hook is `entry: bash` with `args: ['-c', <script>]`. pre-commit appends filenames after the
script string, so the first becomes `$0` and never enters `"$@"` — on a single-file commit, the
common case, the loop body never ran and the hook reported Passed having measured nothing.
ADR-0022 leans on this hook as the enforcement for a mandatory `metadata.version`, so the vacuous
green was the whole gate.
Implementation notes:
- An arg0 placeholder absorbs `$0` so every filename lands in `"$@"`.
- Checks now run against the YAML frontmatter block only, extracted with awk. The old
`grep -A10 "^metadata:"` matched a `metadata:` inside a body code fence, spanned past the block
into a following `source:` entry's `version:`, accepted any indentation, and missed a `version:`
more than ten lines in. An unreadable frontmatter block is now an error, never a pass.
- The value is asserted against three-part semver. `write-docs` carried "1.0" through the entire
ADR-0022 retrofit undetected, which a presence-only check cannot catch.
Impact: `tests/test-skill-frontmatter.sh` is the first test this hook has ever had. It drives the
real `entry`/`args` composition read out of the config rather than a copy of the script, which is
the only shape that catches the arg0 bug; against the pre-fix hook it scores 7/20.
gates.md described the hook wrongly in both directions and is rewritten, with a carve-out
explaining why this one stays a shell parser next to the "python3 and PyYAML are hard
requirements" reasoning that argues otherwise.
Refs: #127
ADR: 0022
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EeH8SCbcrCAQrtymkNuhKP
Retrofits all 39 skills to ADR-0020's description/body context contract, then fixes what six rounds of independent review found in that retrofit — including four ways the hot gate itself failed open.
Closes#99, #107, #108, #110, #111, #114, #115, #120.
## The retrofit (waves 1-5)
| | Start | Now |
|---|---|---|
| Description FAILs (>400 chars) | 26 | **0** |
| Body FAILs (>900 words, body-only) | 9 | **0** |
| Dangling routing targets | 2 | **0** |
| `Kyberforge.CompositionNote` | 10 | **0** |
| Preload tax | 21,005 chars | **~10,500** |
Under the 12,000-char success criterion. Per-wave detail is on #99.
## The review fixes
**The gate failed open four ways, three of them found after the retrofit shipped.** An unrecognised follower token made a dangling target vanish. A skill directory with no `SKILL.md` resolved as a valid target, so a commit could be green locally and red in a fresh clone — three existing fixtures were relying on that, one of which made the install-leak A/B pass vacuously. Then the free-standing `/name` sweep turned out to be gated on the sentence carrying a boundary marker, so route notation in any other sentence was invisible — not an ERROR, not a SUGGESTION, not an INFO — which left the documented "`/name` always blocks" promise false from a second direction. All four fixed and pinned.
**Two checks were silently not running.** `validate-provenance.sh` checks 7-8 were dead across nine skills. Waking them exposed a deeper problem: they assume `Research doc:` names a source index, but 30 of 121 entries point at topic content documents, so every new check-7 INFO was a false positive and check 8 was saved from a false-FAIL flood only by an *unannounced* skip. Checks 7/8 are now scoped to source indexes and every skip announces itself (#121).
**The retrofit's own anti-goal, four times.** ADR-0020 warns that a blunt gate gets satisfied by deleting content rather than relocating it. `diagnose` and `skill-audit` relocated prose and then read it unconditionally; `prototype` and `vale-config` deleted rules outright that survived nowhere. All four addressed.
## Verification
- `bash tests/run-tests.sh --strict` — 24 suites, 0 skipped, 0 failed
- `bash tests/run-bats.sh` — 325 tests, 0 failures
- `pre-commit run --all-files` — 17/17
- `pre-commit run --hook-stage pre-push --all-files` — 16/16, with `apm marketplace check` and `apm pack --check-clean` run against the remote, not skipped
- `scripts/skill-size-check.sh` over all 39 skills — rc 0, 0 ERROR/FAIL, SUGGESTION-only
- Preload tax measured at **10,498 chars**, max description 390 — both inside budget
- Every new test proven non-vacuous by a deliberate mutation of the behaviour it covers
**Per-commit sync, stated accurately:** the ten commits from the latest review round each pass `check-plugin-content-sync` in isolation, verified by checking each out in a detached worktree with a clean between. The earlier gitea window (`dfacf05..bedbd1d`, nine commits) does **not** — its mirror was regenerated in one batch at `bbc7300`. An earlier revision of this description claimed the property held for every commit; it does not, and a bisect through that window lands on a red commit. **Squash-merge** to collapse it, or accept that this range is not bisectable.
## Version bump
Six plugins and the catalog take a **patch**, not a minor. The branch is **89 commits — 40 `fix` / 30 `refactor` / 12 `docs` / 5 `chore` / 2 `test` — zero `feat`, zero `!`, zero `BREAKING CHANGE`** — and adds no skill, agent, command or hook. (Two earlier revisions of this section cited a stale histogram, most recently 78 commits; the figures above are measured at HEAD.) Both rules this repo ships (`forge/references/version-bump.md`, landing in this PR, and `git-commits/references/conventional-commits-spec.md`) make that a patch, and the catalog set is unchanged at 7 entries.
Not settled by that: four published files were removed from the installed tree, three moved, and `caveman` gained `disable-model-invocation`, retiring its old triggers. Under a strict reading those are major-class and currently ship under `refactor:` with no marker. Whether the deployed skill surface is a public contract is written down nowhere — worth deciding, but it outlives this PR.
## Deliberately not in scope
#112 (cherry-pick ownership, now resolved in favour of `git-commits`), #113 (`rtk git` normalisation), #116 (research fan-out), #101 (audit-skill merge), #122 (non-spec skill-root files), #123 (no PRD producer) stay open. #117 is the one worth reading: the contract's remedy is to move prose into `references/`, which is exactly where neither the size gate nor Vale looks — and the blind spot is wider than #117 currently records, since there is no root `.vale.ini` at all, so every ADR, `CONTEXT.md` and `README.md` is unlinted too.
That blind spot let this branch carry two `level: error` `Kyberforge.SentenceOpenerThereIs` violations into `references/` files it created — `provider-adapter-author/references/provider-matrix.md:31` and `agent-audit/references/finding-criteria.md:95`. Both are reworded in `afadaae`, confirmed by routing each file through the audit's own `vale-wrap.sh` (1 error each before, 0 after). Five further occurrences sit in `references/` files already on `main`; those are the pre-existing corpus and stay with #117, which is the real fix.
Also unfixed and not this PR's: `apm install` appends a duplicate `SessionStart` entry to `.claude/settings.json`, so a fresh clone cannot get pre-push green without an edit AGENTS.md warns against. Reproduces identically on `main`.
Co-authored-by: Defame1297 <gitea@rkdr.net>
Reviewed-on: https://git.dev.rkdr.net/Defame1297/holocron/pulls/129
Co-authored-by: Claude Code AI - Gitea MCP <claude@noreply.git.dev.rkdr.net>
Co-committed-by: Claude Code AI - Gitea MCP <claude@noreply.git.dev.rkdr.net>
Why: two blind verifiers re-ran the five preceding commits and found four
defects of the same class this branch exists to close -- a confidently stated
measured claim that does not survive re-measurement -- this time inside the
fixes themselves.
- AGENTS.md:41 still carried both phrasings c68e864 reports having corrected.
`grep -rn repo-defined` returned exactly one hit repo-wide: that line, in the
file every session preloads. 4d336bb edited the line directly above it.
- ADR-0021 asserted twice, in the section justifying that no gate is added,
that the ADR-0020 validators "never open an apm.yml". All three open and
yaml.safe_load it (skill-size-check.sh:342, both validate.sh). The conclusion
survives -- none reads the description: key, and their globs are SKILL.md and
*.agent.md only -- but the stated mechanism is falsified by one grep.
- architecture.md said the ADR directory holds 20 numbered ADRs; c7ba3d2 made
it 21, and c68e864 audited that file for exactly this class of stale count.
The number is dropped rather than corrected: `ls docs/adr/` is already the
index, so a count in prose is a second thing to maintain.
- gates.md's new three-verdict table said `-> name` promotes an unresolved
target to ERROR. Reproduced with fixtures: NAME_HYPH (skill-size-check.sh:543)
requires a hyphen, so `-> gitea-prs` is checked and `-> triage` is not
extracted at all, and the unicode arrow is never recognised. The SUGGESTION
text advises that spelling, so taking its advice can silence the finding. The
gap is now documented as a defect; nothing covers it, since the one arrow case
in test-adr0020-targets.sh happens to use a hyphenated target.
Implementation notes:
- AGENTS.md:48's coverage claim is shrunk rather than chased. Restoring six
glossary entries did not make it true: 12 more sampled terms are undefined,
three of them (trigger/capability/boundary clause) used inside CONTEXT.md
itself. It now says CONTEXT.md is the glossary and is not exhaustive.
- CONTEXT.md's output profile and near-miss entries are corrected against their
sources. The first stated a false exclusion -- .github/plugin/plugin.json IS
apm-generated; only the marketplace mirror has no profile. The second
inverted its source's referent: description-quality.md defines a near-miss as
a query, not a sibling skill.
- The strict-mode message named jq, which no suite guards on (`command -v jq`
appears nowhere in tests/), while omitting python3/PyYAML, which three do.
- README's git and gitea bullets now name git-workflow and gitea-workflow.
ADR-0021 leaves README the only inventory and architecture.md now points at
it, so the two bullets that were short had to be completed.
- ADR-0018's 2026-08-14 correction is marked superseded in place. It asserted
machine state in the present tense that its own 2026-08-17 note retracts.
- ADR-0021's remaining errors: six files -> four (measured from de84d1b), the
wiki description's length 114 -> 96 chars, the codex self-contradiction, the
cost argument overstating bumps already owed for any skill addition, and two
claims about files this branch went on to edit.
- The "15 of 17 suites" figure is restored where I had removed it: it is a dated
record of one incident, not a live count, and four sites now describe it the
same way.
Impact: 16/16 pre-push hooks pass, suite 24 passed 0 skipped 0 failed. No
behaviour change; every edit is prose or a comment.
Refs: #105
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TmFqzpuExLJv3m114XVE9w
Why: the relocation into gates.md and architecture.md moved text faster than it
verified it, and a review found eight assertions that do not survive contact
with the repo.
- gates.md cited docs/research/examples/, which does not exist; the tree is at
plugins/kyberforge/docs/research/examples/. The same wrong string survives at
ADR-0013:98, where it originated, and is tracked separately.
- gates.md's description-budget arithmetic was built on 23,427, a figure
ADR-0020 measured at f9b919d and pins there, and compared a name-inclusive
total against a description-only ceiling. Dropped rather than re-measured,
following the precedent this branch set for CONTEXT.md's token figure: a
second live copy is a second thing to go stale.
- gates.md listed "every boundary-clause routing target must resolve" as a hard
FAIL. skill-size-check.sh emits unresolved targets as SUGGESTION by default,
promotes to ERROR only when terminal and either route-notated or corroborated
by a resolving target in the same sentence, and reports INFO DID NOT RUN when
no universe resolves. Verified with five fixtures; replaced with a
three-verdict table.
- gates.md and README called `pre-commit run --hook-stage pre-push --all-files`
the whole push gate. check-release-needed.sh exits 0 unless
PRE_COMMIT_REMOTE_BRANCH is refs/heads/main, which only the real git hook
exports -- its own header comment titles this a "Known gap".
- "repo-defined" was loose: the two meta hooks are also declared here, and what
separates them is repo: meta from repo: local.
- architecture.md claimed `when:` appears in two of 39 skill sources. Exactly
one SKILL.md carries it; the second hit is a META.md. The likely origin is
skill-implementation-workflow.md:233, which claims META.md sits alongside
every skill when one exists in the whole tree.
- architecture.md said core/AGENTS.md is "deployed beside" CLAUDE.md.
deploy-manifest.sh sends them to ~/.claude/ and ~/.agents/ respectively; the
relation is import, not adjacency.
- gates.md's see-also cited ADRs as bare stems where its neighbours use paths.
Implementation notes: architecture.md's closing pointer sent readers to the
published description "for what a consumer actually gets", which was true
against an enumeration and is not after ADR-0021. It now names the boundary
relationship and points at the skills tree and README for an inventory. README's
bin bullet gains caveman and zoom-out, since ADR-0021 leaves it the only place
an inventory lives.
Impact: 16/16 pre-push hooks pass. Deliberately not fixed here and tracked
separately: the 12 pre-commit-stage hooks gates.md does not document, its own
SentenceOpenerThereIs violation, and README's missing scripts/install.sh step.
Refs: #105
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TmFqzpuExLJv3m114XVE9w
Why: the review found architecture.md's plugin table and README's plugin list
were both written by enumerating what happened to be in each plugin, so both
went stale immediately — README credited `git` with pull requests it has no
skill for, and both omitted `pc-author`/`pc-run`. bb9158d fixed this same class
on `core` in August and it recurred here, so the fix is to stop enumerating in
the place whose job is routing.
Implementation notes:
- architecture.md's table now states routing boundaries only, with a note saying
so and pointing at each plugin's published apm.yml description for the actual
inventory. Two boundaries are named explicitly: `core` vs `kyberforge` (kept),
and `git` vs `gitea` — wire protocol against a local clone versus the forge's
HTTP API, which is why git-branches and gitea-branches are not duplicates.
- The `git` row is widened to cover git hook tooling rather than moving
pc-author/pc-run elsewhere. pre-commit manages .git/hooks/, so the placement
was always right and the row was simply under-described.
- README's setup block had a comment where step 2's command should be. It now
carries `pre-commit install -t pre-commit -t commit-msg -t pre-push`, verified
against the three stages in .pre-commit-config.yaml and the three hooks in
.git/hooks/. pc-run is still named, as the option rather than the only path.
- README:11 said each plugin carries agents, hooks and MCP servers. Only
kyberforge ships hooks and only bin ships an MCP server.
- gates.md:30 claimed its hook list was in config order; it is grouped by
concern, which is the better layout, so the claim is corrected to match.
Impact: docs-only. gitea's published description is corrected separately, since
that regenerates consumer-facing manifests.
Why: 1929ffd and b9c7762 preserved every constant, hook ID and error string,
but two don't-re-litigate notes were lost. Both were guard-rails — they fired
from preloaded context, before the mistake. Restoring the sentence to an
on-demand spec doc restores the text without restoring the function, since an
on-demand file is opened after a plan is formed, not before.
Implementation notes: placed by when each note must fire, not by what it is
about.
- "Do not expect `apm pack` to refresh the .github/plugin/marketplace.json
mirror" now lives in the DRIFT failure message of the script and hook that
already catch that exact mistake. It costs no preloaded tokens, fires at the
moment of the error, and cannot be missed. No test asserts on that message;
--check and shellcheck both pass.
- Plugin self-containment has no gate that fires on it, so it goes in
architecture.md's Plugin model beside "self-contained plugin units", stated as
the constraint it is rather than a description, with the two consequences that
make it load-bearing: the duplicated Vale styles (ADR-0014) and ADR-0020's
constants copied into three validators.
Impact: the every-session set is unchanged — neither note returns to AGENTS.md.
Why: CONTEXT.md is an instructed every-session read at 33,799 bytes (~8,450
tokens), and CONTEXT.md:17 layered docs/VISION.md on top. After the AGENTS.md
trim, that left ~9,650 tokens of instructed reads sitting behind a file whose
own format contract — grill-with-docs/CONTEXT-FORMAT.md:43, "Keep definitions
tight. One sentence max." — it was not following. 22 glossary entries averaged
190 words; the top four were 55% of the file, and one ("Vale audit prefilter")
was 1,444 words of pre-commit forensics filed as a definition.
Implementation notes:
- CONTEXT.md rewritten to CONTEXT-FORMAT.md's prescribed template: ## Language
(five clusters, 22 terms with _Avoid_ aliases), ## Relationships,
## Example dialogue, ## Flagged ambiguities. 33,799 -> 9,762 bytes.
- Vale prefilter forensics moved to docs/spec/gates.md under nine subsections:
the two-copy style layout, vale-wrap.sh and the Vale 3.15.2
text.frontmatter.description limitation, the --config argv defect (E100),
glob scoping, the rule inventory, and 0-files-means-NOT-RUN.
- Instruction-file format and the bidirectional-reference principle moved to
docs/spec/architecture.md, the latter flagged as aspirational: no instruction
file carries a `when:` field, only 2 of 39 skills do, and the reference
scanner script it names does not exist.
- Added a per-plugin scope table to architecture.md so "which plugin owns this
skill" survives the trim, and corrected its claim that the content index
lives in providers/claude-code/CLAUDE.md — that file is now two import lines
and the index sits in core/AGENTS.md.
- "Repo and Gitea are the only source of truth" moved from CONTEXT.md's
Principles into AGENTS.md session rules; it was operative guidance in a
glossary. docs/VISION.md and LESSONS.md added to the on-demand list.
- The apm-consumed install entry (432 words) was deleted outright: all four
consequences are already carried by README.md, ADR-0018, gates.md and
AGENTS.md.
- ADR-0013, ADR-0015 and ADR-0017 each pointed at CONTEXT.md sections that
moved; amended with dated supersession notes rather than left dangling.
Impact: the every-session set drops from ~15,700 to ~4,140 tokens across both
passes (-74%). The deleted "lint plugin" entry was also stale on a safety
claim — it said lint-runner inherits Edit, but ADR-0016 restored
`disallowedTools: Edit, Write, NotebookEdit` and CONTEXT.md was never updated.
Refs: #99
Why: AGENTS.md is preloaded into every session via CLAUDE.md's @AGENTS.md
import, so every word is a tax paid whether or not it is relevant. It had
grown to 3,371 words (~4,550 tokens), 75% of it a single "Setup and testing"
section that was mostly neither: roughly 1,600 words were gate forensics —
why a hook is shaped the way it is, what was tried and rejected, verification
numbers — and only ~390 words were genuine one-time setup.
Implementation notes: split three ways by audience rather than by heading.
One-time setup, prerequisites and test commands move to a new root README.md,
which did not previously exist. The gate forensics move to a new
docs/spec/gates.md, preserving every constant, hook ID, error string and
tried-and-rejected note (policy.fetch_failure_default, the removed fallback
frontmatter reader, extending skill-size-check's files: pattern to agents,
tidying .claude/settings.json out of the pretty-format-json exclude list) —
these exist to stop settled decisions being re-litigated, so none were
dropped. AGENTS.md keeps only what applies every session, at one clause of
rationale per rule. The .apm/-mirror section collapses to a pointer because
docs/spec/architecture.md already covers it in full. The hot ADR-0020 gate
counts stay in AGENTS.md deliberately: they block any skill edit today.
Also corrects docs/spec/architecture.md's stale claim of 19 ADRs; ADR-0020
landed without updating the count.
Impact: per-session preload drops from ~4,550 to ~1,116 tokens, a 75% cut.
agentsmd-audit passes: secrets clean, drift clean, 4 informational findings
for sections deliberately relocated to the README.
Why
---
ADR-0018 left deployed skills tracking the remote default branch with nothing
watching for drift. The mechanism that was supposed to cover this,
scripts/git-hooks/post-push, could never have worked: git has no client-side
post-push hook. install.sh copied it into .git/hooks/ so it looked installed,
and it had never once fired. Issue #78 reported it as skipping the gitea
plugin; it was skipping everything.
Refreshing on push was also the wrong shape. Your install goes stale when
someone else merges, so a push of your own is neither necessary nor sufficient
for staleness to have occurred.
Implementation notes
--------------------
kyberforge ships a SessionStart hook (startup matcher only) that runs
`apm outdated`, and when anything is behind runs `apm update --yes` and returns
reloadSkills:true so the running session picks up redeployed content. It exits
silently with no apm.lock.yaml present, which keeps it inert for hosts that
installed this plugin natively rather than through apm.
Two findings drove the wiring, both verified rather than assumed:
- apm resolves ${CLAUDE_PLUGIN_ROOT} against the installed package root, and
`apm pack` keeps only *.json from .apm/hooks/. A .../hooks/<script> reference
therefore points into the generated mirror where the script does not exist —
apm reports "Hook script not found" and deploys a hook aimed at nothing. The
reference must be .apm/-relative, and a test pins it.
- apm's executable-trust gate is OFF unless apm.yml carries an `executables:`
block; until now every hook, bin and MCP primitive a dependency shipped would
have deployed unprompted. Root apm.yml now enables it. The allow key is
version-pinned by apm's design, so a kyberforge version bump silently blocks
the hook until the key is bumped too — called out in the block and the ADR.
Also corrects ADR-0018 and AGENTS.md, which named `apm install` as the refresh
command. It is not: `apm install` deploys from apm.lock.yaml's pinned commit
and does not re-resolve refs. `apm update` does.
Impact
------
Session startup costs ~0.7s when current and ~10.4s when six packages are
behind. Auto-refresh rewrites apm.lock.yaml, so an unexplained modification to
it after opening a session is expected; the emitted notice says so.
.claude/settings.json stops being exactly {"hooks": {}} once the hook lands
there — the merged entry is apm's own output, and the rule that nothing
repo-authored goes in that file is unchanged. .claude/hooks/ and the
.claude/apm-hooks.json sidecar are gitignored install output.
The hook cannot install itself: dependencies resolve from the remote, so it
takes effect only after this merges and `apm update` runs once against the new
default branch.
scripts/git-hooks/ is now empty. install.sh's copy block is kept and
test-git-hooks-install.sh synthesizes its own fixture, so the mechanism stays
tested without requiring a dead hook to exist.
ADR: 0019
Refs: #78
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01X7GvKuJfy2WrdBmUttV4DT
Why:
The repo published apm packages but consumed them the old way — `claude plugin install
<name>@holocron`, six plugins enabled per project. Dogfooding stopped one layer short of the
install tooling kyberforge itself ships.
Implementation notes:
- Root apm.yml declares the six packages as dependencies.apm git+path objects against the
holocron remote. Object form over `<name>@holocron` aliases on purpose: an alias first needs
`apm marketplace add`, which writes to ~/.apm/marketplaces.json — user scope, absent on a fresh
clone. Unpinned against the default branch, matching the autoUpdate the native install had.
- apm.lock.yaml is committed; .claude/skills/, .claude/agents/ and apm_modules/ are gitignored
regenerable install output. Committing the deployed skills would add a third mirror of content
ADR-0017 already governs two copies of.
- .mcp.json is generated by apm from plugins/bin/.mcp.json, so the obsidian MCP server survives
the switch.
- .claude/settings.json is reduced to {"hooks": {}}. apm replays the install into a scratch tree
and diffs, so any repo-owned key there is permanent drift that fails apm-audit-ci. Nothing was
lost: enabledPlugins was empty after the uninstall and the only hooks entry was PreToolUse: [].
- tests/run-bats.sh and tests/run-tests.sh exclude apm_modules/. It holds a full copy of every
plugin, and a copied .bats file resolves its helpers against the dependency root rather than
this repo — 334 tests, 167 failures before the exclusion.
Impact:
Skills are now unnamespaced — `git-commits`, not `git:git-commits` — because apm deploys plain
project skills with no plugin to prefix. AGENTS.md, CONTEXT.md and docs/spec/architecture.md are
updated accordingly. Root apm.yml now declares dependencies, which arms apm-audit-ci's
lockfile-exists check for the root manifest. External consumers are unaffected: the marketplace
manifests are untouched and `apm pack --check-clean` stays clean. Project scope only.
ADR: 0018
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01X7GvKuJfy2WrdBmUttV4DT
AGENTS.md told an offline agent to push with SKIP=apm-marketplace-check and
asserted that hook was "the only one whose failure mode is 'no network'".
Running all 12 pre-push hooks under a network namespace shows two fail, for
one shared cause: apm-pack-check-clean resolves the same remote entry. An
exact pin does not remove the ls-remote, so both hooks are named now.
AGENTS.md also said everything in a plugin root except .apm/ is generated.
Plugin roots carry hand-authored README.md, docs/, bin/, sources.md and
.mcp.json, so an agent would hunt for an .apm/ source that does not exist or
refuse the edit. The rule is positional: immunity belongs to the plugin root,
and anything inside a mirrored directory is still rm -rf'd.
ADR-0017 said apm strips a hooks field. The real loop is (agents, skills,
commands, instructions) -- hooks absent, instructions never mentioned -- and
it can never fire, because synthesize_plugin_json_from_apm_yml only emits the
eight identity fields. The decision stands; the mechanism was overstated. Its
mcpServers amendment is rewritten for the pointer payload and now records the
real reason: inlining bypassed apm's credential sanitizer.
ADR-0015's owner.email and version-pin passages are corrected against the apm
source, and ADR-0016 gains the disallowedTools amendment. agent-audit's
allowlist is data, so it gains disallowedTools too -- the ADR and the
validator that enforces it had come apart.
architecture.md described a root CLAUDE.md that imports two files (it imports
one, plus an RTK block) and pointed at an ADR index that does not exist.
Seven skill READMEs listed tests/ files the mirror strips, promising installed
users files their install lacks; those rows are marked source-only, with the
depth-4 template tests explicitly called out as surviving. And
plugins/kyberforge/hooks/README.md, deleted during the conversion and
preserved nowhere, is restored to a path the mirror does not own -- verified
by running a sync against a scratch copy.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01X7GvKuJfy2WrdBmUttV4DT
Documentation asserted things the code no longer did, which is how several of this
round's defects survived three review passes.
- `docs/spec/architecture.md` still described the pre-APM model — "each plugin has a
`plugin.json` manifest" — when no such file exists. AGENTS.md routes agents here
for the current structure, so it was live drift, not archive. Also cited ADR-0012
where ADR-0003 is meant.
- AGENTS.md never said `.apm/` is the sole hand-edited source, while the generated
mirror is byte-identical with no marker — an agent reading only AGENTS.md would
edit the mirror and find out at pre-push. It also omitted that `apm` and `jq` are
now required to push, unlike the `vale` bullet that exists for exactly that reason,
and understated the pre-push gate. `apm marketplace check` hard-fails offline and
`--offline` does not help, so the `SKIP=` escape hatch is documented rather than
new machinery built.
- ADR-0017 carried hardcoded line numbers that drifted twice within one PR, and said
`mcpServers` reinjection was real-syncs-only where the script's own header says
both modes. Line numbers dropped rather than corrected.
- ADR-0015 asserted issue #90 was closed. It is open. Reworded to defer to the
issue's own state rather than depend on someone remembering to close it.
- ADR-0014 said both audit skills pass `--config`; both SKILL.md files say pass none,
and passing one fails with E100. The ADR was wrong.
- ADR-0007 cross-referenced an archived ADR-0011 whose number was later reused.
Disambiguated with a note — renumbering a published ADR rewrites an immutable
record and breaks every existing citation.
- CONTEXT.md claimed `lint-runner` is report-only via a missing `Edit` tool.
Plugin-scope APM agents cannot express `tools:` (ADR-0016), so it is report-only by
instruction now; ADR-0016 accepted that regression but CONTEXT.md was not updated.
- Recorded two undocumented consequences of the conversion: `displayName` dropped
from all six compiled manifests and `owner.email` from the marketplace, and
`mattpocock-skills` silently version-pinned and manually maintained.
- Wrote the version-bump policy issue #90 specified but never delivered. Its previous
carrier, `marketplace-author`, was deleted in this PR, leaving the per-package rule
documented nowhere.
- README fixes: kyberforge listed skills belonging to the `git` plugin and a deleted
hooks path, `bin` advertised an agents directory it never had, and the docs index
listed files that do not exist.
Refs: #90
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01X7GvKuJfy2WrdBmUttV4DT
## Why
overview.md described the chunk-based delivery model, which is superseded
by the marketplace/plugin pivot. architecture.md was equally stale: it
described .agents/skills/ as the canonical skills source (directory does not
exist), a provider-manifest.sh symlink mechanism (never built), and sync.sh /
init-project.sh as existing scripts (Chunk 6, not yet built).
## Implementation Notes
- overview.md deleted; all cross-references scrubbed from AGENTS.md, CONTEXT.md,
and three notes/research files
- architecture.md fully rewritten: content deployment model reflects actual
install.sh behaviour (DEPLOY_FILES / DEPLOY_EXECUTABLES / DEPLOY_DIRS);
plugin model section added listing all 5 plugins; directory structure section
removed (was describing a layout that no longer exists)
- "Chunk 6" phase label → "planned"; "chunk workflow" removed from AGENTS.md
description
- Fixed broken path docs/HUMANS.md → docs/wiki/HUMANS.md in governance layer
and core/instructions/governance.md
Refs: #15
## Why
ROADMAP.md was a static file that duplicated tracking information now
owned by Gitea milestones and issues. Keeping it created a maintenance
burden — references drifted out of sync with the actual state of work,
and agents were directed to read it when the source of truth had moved.
## Implementation Notes
All inbound references replaced with either the relevant Gitea milestone
("Skills & Agents") or removed where the context made them redundant.
Test assertions that verified ROADMAP.md content removed; test output
strings updated to drop the ROADMAP cross-reference instruction.
## Impact
Agents no longer read docs/ROADMAP.md at session start. Gitea milestones
and issues are the canonical source for roadmap and open-question tracking.
---
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Update docs to reflect pre-commit migration and cleanup:
- spec/overview.md: removed phantom test file references
- ROADMAP.md: removed references to non-existent test files
- LESSONS.md: removed reference to setup-hooks.sh bug
Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
## Why
The convention requires living spec files to be updated in the same
commit as any behaviour change. Adding agent-author to kyberforge
without updating overview.md would leave the spec stale.
## Impact
kyberforge plugin entry now accurately reflects its three current skills
(skill-author, skill-audit, agent-author) and drops the outdated
reference to create-plugin, marketplace-architect, write-skill, and
write-eval which are no longer in the plugin.
---
Refs: #10
ADR: docs/adr/0015-agent-author-dual-provider-scaffold.md
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
No longer needed — kyberforge plugin-create provides a bundled template that
serves as the canonical scaffold reference. Remove hello-world from marketplace
manifests and update docs accordingly.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Updates overview.md and architecture.md to document the kyberforge plugin,
the moved skills and evals, the removal of templates/, and the new plugins/
directory in the repo structure.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Complete 2026-05-18 workstream for write-skill refactor (issue 0018 phase 1).
Grill output (handoff in docs/issues/0018-factory-write-skill.md):
- 6-section standard replaces 8: Role and When/When not dropped (not in
agentskills.io spec; description carries trigger scope and negatives)
- Frontmatter reduced to 3 fields; provenance moves to META.md
(progressive disclosure — not loaded at every skill scan)
- SKILL-TEMPLATE.md and META-TEMPLATE.md as authoritative copy-fill artifacts
- CATEGORIES.md as self-contained category reference in skill directory
- Copy and fill explicitly split into separate process steps for determinism
New files in .agents/skills/write-skill/:
- SKILL-TEMPLATE.md — 6-section template with XML blocks and inline examples per section
- META-TEMPLATE.md — provenance schema with inline-commented YAML; source vs references explicit
- CATEGORIES.md — self-contained category table (no runtime dependency on factory docs)
- META.md — write-skill's own provenance (v1.1, self-authored)
SKILL.md rewritten: 8-step process, XML blocks (<requirements>, <steps>, <checks>),
3-field frontmatter, copy-then-fill steps explicit.
Supporting docs updated:
- skill-implementation-workflow.md: SKILL-TEMPLATE.md as authoritative template;
source:/references: now reference META.md; when: marked resolved
- factory-integration-decisions.md: frontmatter spec corrected
- ROADMAP.md: authoring standard description updated
- CONTEXT.md: Source field entry corrected; META.md added to glossary
- docs/spec/overview.md: 2026-05-18 refactor entry added
- docs/issues/0018: handoff status updated; acceptance criteria marked complete
LESSONS.md: 3 entries added in grill session (cargo-culted body sections,
provenance fields in frontmatter, copy-fill determinism) + 1 from implementation
(planning meta-commentary does not belong in deployed artifacts).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds write-eval, the first factory meta-skill. Produces eval.yaml test
files for skills following the two-section schema (trigger_tests +
output_tests) with provider-agnostic string assertions and show-plan-
then-merge-on-rerun behaviour. Hand-written bootstrap — subsequent
skills will use write-eval to produce their own evals.
Also tightens skill-implementation-workflow.md step 5b: per-section
options walk-through is now a named gate before writing, separate from
the synthesis grill. LESSONS.md entry added.
HITL behavioral test pending.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Create AGENTS.md at repo root and core/AGENTS.md as provider-agnostic
sources of always-on rules. Slim both CLAUDE.md files to thin adapters.
Deploy core/AGENTS.md → ~/.agents/AGENTS.md via deploy-manifest.sh.
Update three test suites to check correct locations post-refactor.
All automated tests pass (57 instructions, 106 install, 25 governance).
HITL behavioral test plan in test-instructions-and-docs.sh scenarios 9–12.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
14 issues created covering AGENTS.md refactor prerequisite, skill
implementation workflow grill, bootstrap skills (write-eval, write-skill),
remaining factory skills, and one issue per skill category group through
to chunk closure. All HITL; acceptance criteria for 0017-0028 to be
refined after 0016 grill session.
Doc updates: CONTEXT.md PRD/issue scope clarified (HOW distribution
across architecture-review and issue design notes); ROADMAP.md housekeeping
updated with bootstrap order and issue range; spec/overview.md recent
changes entry added; PRD updated (skills-index: delete → update).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Skills-index is now explicitly the canonical build reference for trigger
descriptions, constraints, and categories. Roadmap entry updated with
category breakdown, flat-path naming reconciliation (ADR-0009), authoring
standard reference, and delete-when-done instruction. Spec overview updated
to match.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
13 manual scenarios run across instructions and governance layers (two
rounds for failures). Fixed four rules that lost to RLHF defaults:
- Exploratory question format: tightened with boundary framing; added
@import CONTEXT.md to repo CLAUDE.md and a standing rule to check
docs/adr/ and ROADMAP resolved entries before answering design questions
(3-round iteration to resolve)
- File-edit intent: added counter-example to stop clarification-seeking
- Push confirmation: reframed as "do not call the tool" not "ask first"
- Secrets rule: extended to cover credential reproduction in response
text and usage examples, with explicit placeholder requirement
Scenario 4 (push confirmation) inconclusive — no remote configured.
Governance scenario 3 (HITL on real infra) untestable — Nginx not installed.
Both share the same root cause: agent delegates to permission system.
Also corrects stale skill list in docs/spec/overview.md (12 actual
deployed skills vs 16 names previously listed).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add LESSONS.md as the long-loop feedback log at repo root. Patterns
observed during development graduate to standing rules when three or
more entries appear.
Introduce docs/spec/ as the living spec layer: overview.md (deployed
state) and architecture.md (directory structure, install pipeline,
provider model, governance layer). Refactor docs/VISION.md to goals
and intent only — architecture content moved to docs/spec/architecture.md.
Update CLAUDE.md and CONTEXT.md to reference the new spec files.
Close issues 0013 and 0014. Update ROADMAP and factory integration
note to reflect completion.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
