A review of PR #85's last two commits (1164f3a, 4d018af) found the new
release-gate script fails open in four separate ways, and the new drift
check for the duplicated Vale styles only ever detects drift after a
human already hand-edited both copies out of sync.
check-release-needed.sh:
- The `-e` existence filter dropped a RELEASE_PATHS entry from the diff
pathspec once it was deleted from the tree, so deleting a path exposed
via .pre-commit-hooks.yaml since the last tag passed the gate clean —
exactly the breakage the gate exists to catch. git diff reports
deletions fine without an existence check; the filter is gone.
- `git diff ... 2>/dev/null || true` turned any git failure (a shallow
clone missing the tag's objects, a corrupted ref) into an empty,
falsely-clean diff. The diff result is no longer swallowed: a failure
now hard-fails with the underlying git error visible.
- RELEASE_PATHS was a hand-maintained array duplicating
.pre-commit-hooks.yaml's entry: paths with only a comment holding them
in sync, and was already over-broad (it swept in validate.sh /
validate-provenance.sh, which no hook entry references). It's now
parsed straight from .pre-commit-hooks.yaml's entry: lines at
runtime, so it can't drift from the manifest and only tracks what a
hook actually exposes.
- `git describe --tags --abbrev=0` accepted any tag reachable from HEAD
as the diff baseline, not just release tags. Added
`--match 'v[0-9]*.[0-9]*.[0-9]*'` so an incidental checkpoint tag
can't shift the baseline and mask a real release-relevant change.
check-vale-style-sync.sh still only detects drift between skill-audit's
and agent-audit's duplicated vale-wrap.sh/styles/Kyberforge copies
(both copies must exist independently per the plugin's no-cross-skill-
path packaging rule — a symlink would break at install time). Added
scripts/sync-vale-styles.sh to regenerate skill-audit's copy from
agent-audit's canonical one on demand, and pointed the sync check's
failure message at it, so fixing drift is one command instead of a
hand diff across two files.
Also recorded, rather than silently left unfixed: check-release-needed.sh
only fires on a local `git push` through pre-commit's pre-push hook — a
PR merged via Gitea's merge button, or CI invoking
`pre-commit run --hook-stage pre-push` directly, never sets
PRE_COMMIT_REMOTE_BRANCH and skips the gate entirely. Closing that needs
a server-side CI job this repo doesn't have yet; documented as a known
limitation in ADR-0014 rather than papered over.
Separately, LESSONS.md's "a clean check can mean nothing ran" entry was
marked **Graduated** without ever being promoted per the repo's own
graduation rule (3+ instances → a standing doc, marked
`[graduated → target file]`). Actually promoted it into
core/instructions/testing.md and fixed the marker.
tests/test-check-release-needed.sh gained 4 regression tests, one per
check-release-needed.sh fix above, each verified to fail against the
pre-fix script and pass against the current one.
Verification: bash tests/run-tests.sh (11 scripts + 125 bats, all
passing), pre-commit run --all-files, and
pre-commit run --all-files --hook-stage pre-push all clean.
ADR: 0014
.pre-commit-hooks.yaml now exposes hooks to external consumers pinning
rev: <tag>, but nothing enforced that a tag actually gets cut when the
files it references change — relying on memory is exactly what this
repo's governance rules say to avoid for a repeatable, deterministic
check.
scripts/check-release-needed.sh hard-fails at pre-push, but only when
PRE_COMMIT_REMOTE_BRANCH (set by pre-commit's hook-impl) is
refs/heads/main: it diffs .pre-commit-hooks.yaml's referenced paths
against the last tag reachable from HEAD, and fails if either no tag
exists yet or something changed since. It's a silent no-op on every
other branch — hard-failing on feature-branch pushes mid-review would
force a premature tag on a commit that might not survive a
squash-merge, the exact risk the repo: local (vs. pinned self-
reference) decision in ADR-0014 already avoids for this repo's own
dev-time gate.
Verified against the real git pre-push hook path (not just the script
in isolation): simulated stdin matching git's pre-push protocol through
.git/hooks/pre-push, confirmed it correctly fires and fails when
targeting main with no tag, and is silent otherwise.
ADR: 0014
Refs: #87
skill-audit/agent-audit's Step 1 resolved vale-wrap.sh/.vale.ini via
`git rev-parse --show-toplevel`, which returns whichever repo the skill
happens to run in. Inside ai-development that works; in any external repo
that installs kyberforge@holocron as a plugin, it resolves to that repo's
own root, which has no .vale.ini — the prefilter silently fell back to
full LLM judgment. ADR-0013 named this as a deliberately deferred gap.
Vale's config/styles/wrapper now ship inside the plugin itself: a
canonical copy in agent-audit/assets/vale/ (Kyberforge + KyberforgeCopilot,
the superset agent-audit needs) and a smaller duplicate in
skill-audit/assets/vale/ (Kyberforge only) — per the no-cross-skill-path
rule already established for plugin cache-installs. Both skills resolve
these relative to their own directory, same as scripts/validate.sh
already does.
A new root .pre-commit-hooks.yaml exposes both copies plus
skill-size-check so any external repo can enforce the same rules via
`repo: <this-repo-url>, rev: <tag>` in its own pre-commit config,
independent of Claude Code entirely — the same mechanism covers CI. This
repo's own pre-commit hook now consumes the identical plugin-bundled
copies via repo: local (not a third root copy, and not a pinned
self-reference, which would lint working-tree edits against the last
tagged release instead of the change being made). Split into
vale-audit-prefilter-skill/-agent hooks after confirming, by diffing the
full corpus against both old and new config before deleting the old
files, that one combined hook pointed at only one copy silently 0-file-
skips the other file type.
scripts/check-vale-style-sync.sh guards the two copies against drift,
wired at pre-push alongside check-manifests.
ADR: 0014
Round-3 review of PR #85 found the "enforcing" pre-commit hook enforced
nothing. Vale's exit code keys on error-level alerts alone: five of the
six rules were level: warning, so they exited 0, and pre-commit hides
output from a passing hook — the alerts were invisible and blocked
nothing. ADR-0013 rejected a report-only trial tier and then shipped one
by accident.
Flatten every rule to level: error. Vale's own exit code is then correct,
so the hook entry drops to a bare vale-wrap.sh call and the graded
error->FAIL / warning->SUGGESTION mapping disappears from both audit
skills: every alert is a FAIL, in the gate and the audit alike. No
ignorable tier, matching shellcheck, the test suite and
conventional-pre-commit.
Delete Kyberforge.VagueQualifier. Measured against the 41 skill/agent
files as they stood before the rule ever ran: 2 hits. One marginal
("very different" -> "fundamentally different"), one an unfixable false
positive — caveman/SKILL.md quotes "of course" as an example of filler,
a mention not a use — which forced the only Vale suppression comments in
the repo. Those four lines go with it; two of them were dead anyway,
suppressing a frontmatter-scoped rule on a body line. Held-out prose (273
files) fired 15 times, 9 inside out-of-scope research examples and the
rest one word in two idioms in a single doc. SentenceOpenerThereIs
survives: 22 held-out hits, both in-corpus hits clean rewrites, zero
suppressions.
Widen .vale.ini's globs to [**/SKILL.md], [**/agents/*.md] and
[**/*.agent.md]. The plugins/*/-prefixed globs scoped nothing — Vale's *
crosses /, so they already matched docs/research/examples/**/agents/*.md
and assets/templates/SKILL.md, the two paths CONTEXT.md claimed they
excluded. Scoping is and was the hook's files: regex. The old globs also
hid a silent false negative: a skill outside plugins/ matched no section,
so Vale reported 0 files and exited 0, which both audits read as clean.
They now treat a 0-file run as NOT RUN and fall back to full judgment.
Also:
- vale-wrap.sh resolves relative --config values and file arguments
against the caller's cwd, as vale does, instead of the repo root, which
hard-errored from a subdirectory and silently skipped flattening for
file args that did not resolve from the root. Absolute paths inside the
cwd are relativized so reports cite resolvable paths, not scratch ones.
- vale-run's exit-code model was documented backwards ("exits non-zero
whenever it finds an alert at or above MinAlertLevel") and would have
led anyone following it to build a gate that passes everything. Its
Markdown suppression syntax was MDX-only and does not suppress in .md;
corrected in the skill and its troubleshooting reference, with
backtick/fence exemption documented as the first resort.
- skill-size-check.sh fails only above 500 lines, agreeing with
skill-audit's validate.sh <= 500 pass.
- ADR-0013 and CONTEXT.md amended to match, recording why graded
severities cannot gate.
Verified: 9 test scripts / 15 vale-wrap cases pass; vale-audit-prefilter,
skill-size-check and shellcheck pass --all-files; check-manifests and
claude plugin validate --strict clean. New tests fail against the old
script (3 of them) and pass against the new one.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MCQ648fLSFXPHGZdQ8gn58
Addresses PR #85's outstanding review items after grilling the open
questions against ADR-0013/CONTEXT.md/ADR-0010:
Blocking fixes:
- vale-wrap.sh: replace json.dumps() escaping (which silently defeated
Vale's frontmatter scope on any description containing a quote,
backslash, or non-ASCII char — ~58% of the corpus) with a single-quoted
YAML scalar, substituting a Unicode right single quote for embedded
apostrophes rather than '' doubling (Vale's frontmatter scanner isn't a
full YAML parser and silently truncates on '' too).
- vale-wrap.sh: fix a blank-line-inside-a-folded-description truncation
bug via indentation-based, blank-line-tolerant body capture; narrow
flattening to `>`-style scalars only (`|` already works unflattened).
- skill-audit/agent-audit Step 1: make the vale-wrap.sh invocation
cwd-independent via git rev-parse --show-toplevel, fixing a bug where
no single cwd satisfied all three Step 1 commands.
- styles/Kyberforge/VagueQualifier.yml: prune 17 tokens verified
false-positive-dominated on this repo's own voice via a real corpus
sweep (obvious, clearly, usually, several, simple, easy, completely,
simply, tiny, etc.), keep 13 with real or unattested noise. Revert the
28 prose "fixes" those tokens drove across 14 skill files back to their
original, correct wording, including a functional regression to
caveman/SKILL.md's own filler-word list (a mention, not a use) — now
guarded with vale-off comments against recurrence.
Gaps:
- --minAlertLevel=warning on the pre-commit hook and Step 1 invocation
so warning-level rules actually surface, without collapsing the
FAIL/SUGGESTION severity mapping skill-audit/agent-audit rely on.
- vale-wrap.sh: fix --config=<path> equals-form, absolute-path silent
no-op, and a zero-file-argument stdin hang.
- Route vale-run and lint-runner through a documented wrapper script
when a target repo has one, instead of unconditionally recommending
bare `vale`.
- Wire Kyberforge.VagueQualifier/SentenceOpenerThereIs into skill-audit/
agent-audit's dimension-mapping prose (Body discipline).
- Add plugins/lint/sources.md provenance for lint-runner (ADR-0010).
- Sync both marketplace.json lint-entry descriptions with plugin.json.
- Retune skill-size-check.sh's MAX_WORDS 5000->2900 (measured ~1.6-1.7
tokens/word on this repo's corpus, the old value gated at ~8,500
tokens against a stated 5,000 ceiling); fix the >/>= line-count
boundary and wc -l undercount on files with no trailing newline.
- Document the vale binary as a Setup prerequisite in AGENTS.md.
- Fix SentenceOpenerThereIs's dead regex alternative and add a real
sentence-start anchor/scope.
- Fix a stale docs/research/docs/vale/ index pointer in kyberforge's
docs README (moved to plugins/lint/ in e1a5403).
- Rewrite ADR-0013's Consequences section past-tense to describe what
actually landed, and record the styles-portability limitation
(repo-root placement stays intentional; deferred to a separate
session per this PR's review).
Test coverage: 9 new vale-wrap.sh fixtures (quotes, backslash/unicode,
blank-line paragraphs, --config= form, zero-arg/absolute-path handling,
literal-block no-regression) and boundary-pair tests for
skill-size-check.sh's line/word ceilings.
bash tests/run-tests.sh: 9 scripts + 125 bats assertions, all passing.
scripts/check-manifests.sh and claude plugin validate --strict: clean.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MCQ648fLSFXPHGZdQ8gn58
Deferred item from PR #85 review. Per ADR-0013: cherry-picks two low-noise
rules from trialing write-good/alex against the real corpus (VagueQualifier,
SentenceOpenerThereIs) into styles/Kyberforge rather than adopting either
package wholesale (both are tuned for blog prose and were noisy on this
repo's terse, imperative instruction files - see the ADR's rejected-rule
list). Adds a new skill-size-check pre-commit hook enforcing agentskills.io's
500-line/5,000-token SKILL.md ceiling, currently unenforced. Fixes the 28
resulting violations across 20 existing SKILL.md/agent files so the
enforcing pre-commit hook lands clean.
governance.md/CONTROLS.md were evaluated and excluded as rule sources -
they're org/CI-infrastructure controls, not prose patterns Vale can express.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QUDczvw1H3eEeMD29Q9Lbi
Vale's text.frontmatter.description scope silently stops matching once
the description is a YAML block scalar spanning 2+ physical lines —
the style used by most skills/agents in this repo. scripts/vale-wrap.sh
flattens the description to one line in a scratch copy (preserving the
repo-relative path and total line count) before invoking real vale, and
both audit skills plus the pre-commit hook now call it instead of vale
directly. Also tightens the pre-commit hook's file glob to single path
segments so it can't cross into docs/research examples or asset
templates the way the audit skills' scoped invocations already avoid.
Addresses PR #85 review feedback.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FxG5T8EJDgkABXxuneuFfn
The test's own `git -C "$TEMP_REPO" init` silently re-targets an inherited
GIT_DIR instead of creating a repo in the temp dir when this test itself
runs inside a git hook (e.g. pre-push sets GIT_DIR to the invoking repo's
gitdir). Unset all GIT_* vars at the top of the script so the temp repo
fixture is actually isolated regardless of the calling context.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FNJWdVvdgvZCHi1hZGqgVQ
scripts/install.sh hardcoded $REPO_ROOT/.git/hooks, which breaks under any
git worktree checkout (.git is a file there, not a directory) — this is
what blocks every worktree-based agent from pushing cleanly. Resolve the
hooks directory via `git rev-parse --git-path hooks` instead, normalizing
to an absolute path since git returns it relative to the queried repo root
for plain checkouts but absolute for worktrees.
Also drops `agents`/`skills` fields from plugins/bin, plugins/core, and
plugins/gitea plugin.json where the referenced directories don't exist on
main yet (bin never had an agents/ dir; core and gitea's real skill/agent
content is still pending merge from an in-flight branch) — these were
failing scripts/check-manifests.sh and blocking pushes for unrelated work.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FNJWdVvdgvZCHi1hZGqgVQ
## Why
The repo moved from a chunk-based delivery model with `.agents/skills/`
as the canonical skill source to a plugin model. Several files retained
references to the old model that were either dead code or misleading
framing.
## Impact
- `tests/test-install.sh`: dead `.agents/skills/` test blocks removed;
suite now tests only what `install.sh` actually deploys
- `scripts/deploy-manifest.sh`: `DEPLOY_SKILLS_SRC` variable and stale
`sync.sh (Chunk 6)` comment removed
- `tests/test-git-hooks-install.sh`: fixture stub no longer declares
the removed `DEPLOY_SKILLS_SRC` variable
- `docs/VISION.md`: chunk delivery framing replaced with plugin model
language throughout; manual test plan date updated
- `tests/test-instructions-and-docs.sh`: stale test plan date flagged
as pre-refactor so readers know a re-run is needed
Refs: #15
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
## 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>
## Why
The ## Key rules section was intentionally removed from AGENTS.md as
redundant. Two test assertions — one requiring its presence in AGENTS.md
and one confirming it was absent from CLAUDE.md — are now stale and block
pushes.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
## Why
Two test suites were asserting on paths that were intentionally changed:
- docs/HUMANS.md moved to docs/wiki/HUMANS.md (wiki submodule)
- docs/prd/ deleted after migrating all PRDs to Gitea (#16–#19)
Updated checks to assert the new locations and confirm the old
directories are gone.
---
Refs: #15
Installing kyberforge via the holocron marketplace caches the plugin at a
specific version. After every push, the marketplace clone and plugin cache
need to be refreshed manually — otherwise new skills added since the last
install are invisible until the user runs `claude plugin update` manually.
Adds a post-push git hook that pulls the holocron marketplace clone and
updates the kyberforge cache automatically after every push, eliminating
the manual refresh step.
## Implementation Notes
- `scripts/git-hooks/post-push` is the canonical source; `install.sh` now
copies all files in `scripts/git-hooks/` into `.git/hooks/` on fresh
checkouts, making the pattern extensible for future hooks.
- Hook exits 0 on all failures (warns to stderr) — a stale cache refresh
never blocks a completed push.
- 11 bats tests cover both the hook and the install.sh copy block, using
mocked binaries and a temp-tree fixture to avoid touching real state.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P87CiC58Ru2PPWYTeXtjHT
@CONTEXT.md was deliberately removed from repo CLAUDE.md to reduce
token usage; the test enforcing its presence was no longer valid.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
run-tests.sh calls run-bats.sh which picks up .bats files — testing
run-tests.sh from within bats creates an infinite loop. Shell runner
scripts (run-tests.sh, run-bats.sh) are not bats-tested by design.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add tests/run-tests.sh: discovers and runs all test-*.sh (including
plugin subdirs) and the bats suite; replaces per-script pre-push calls
- Add tests/run-tests.bats: TDD coverage for run-tests.sh behaviours
- Update setup-hooks.sh: pre-push block now calls run-tests.sh
- Fix test-install.sh: remove provider adapter symlink tests (adapter
removed in marketplace migration), guard skills loops on dir existence
- Fix test-instructions-and-docs.sh: content index checks now point to
core/AGENTS.md (where it lives), remove ard/bug dir assertions
- Fix test-setup-hooks.sh: assert pre-push hook calls run-tests.sh
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds a complete cross-cutting skill to install, configure, and manage
@neuledge/context — a local-first MCP server that delivers version-specific
library docs to AI agents via SQLite FTS5.
Includes:
- SKILL.md with 9-step process: install, global MCP registration, per-project
--libs scoping, package management, auth, custom registry, upgrade, uninstall
- setup-neuledge-context.sh: pinned version install, idempotent version check
- secure-context-config.sh: chmod 600 on ~/.context/config.json after auth
- 13-case test suite covering both scripts (all pass)
- eval.yaml with 6 trigger tests and 4 output tests
- references/: context-cli-reference.md, http-mode.md, install-notes.md
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TP4EGbBg3XMcyF28Lx78XJ
setup-hooks.sh now installs shellcheck, jq, and yq if absent rather
than warning and continuing. Follows the same install pattern as
setup-gitleaks.sh (curl + install to TOOL_INSTALL_DIR=/usr/local/bin,
OS/arch detection, pinned versions).
Pinned versions: shellcheck 0.10.0, jq 1.7.1, yq 4.44.3.
The deployed pre-commit hook retains its runtime fallbacks as a safety
net for environments where tools are removed after setup.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TP4EGbBg3XMcyF28Lx78XJ
Two bugs in setup-hooks.sh:
1. awk+mv to replace a marker block created a 644 temp file, losing the
exec bit. chmod +x after every write_block call fixes this. Regression
test added to idempotency block.
2. set -euo pipefail in the deployed pre-commit hook caused grep to exit 1
when no files of a given type were staged, aborting the hook. Changed
all filter pipes to process substitution with || true so no-match is
handled gracefully.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TP4EGbBg3XMcyF28Lx78XJ
Adds setup-hooks.sh and check-manifests.sh as the deterministic
enforcement layer described in docs/research/governance_principles/CONTROLS.md.
- commit-msg: conventional commits pattern check (hard block)
- pre-commit: shellcheck on .sh, jq on .json, yq on .yaml/.yml,
SKILL.md frontmatter validation; optional tools degrade gracefully
- pre-push: full test suite + manifest cross-reference check
- check-manifests.sh: validates marketplace.json plugin sources,
plugin.json skill/hooks/mcpServers path references
- Marker-based blocks (idempotent, composable with gitleaks)
- 33 integration tests across two test scripts
Run scripts/setup-hooks.sh to install into any repo's .git/hooks/.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TP4EGbBg3XMcyF28Lx78XJ
- Remove Fleet, Symbolic oversight, and Data classification tiers from
CONTEXT.md glossary: Fleet is Phase 2 only; the other two duplicate
always-on governance.md content
- Drop now-stale governance test assertions for the removed terms
- write-skill eval: add section-ordering assertion; fix duplicate prompt
across two deterministic tests
- write-eval eval: tighten plan-shown assertion to require per-case
detail (query + type), not just "a list of test cases"
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>
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>
Establishes the global AI development config repo from scratch:
- Chunk 1: repo skeleton, install.sh, statusline, deploy manifest
- Chunk 2: core instructions (coding/git/testing), CLAUDE.md rewrite
(always-on + content index two-tier model), docs restructure,
6 ADRs, ROADMAP.md, .gitkeep placeholders
- Bootstrap skills in .claude/skills/ (to be catalogued and migrated
to .agents/skills/ in Chunk 3)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
