Files
holocron/plugins/kyberforge/.apm/agents/apm-orchestrate.agent.md
Claude Code AI - Gitea MCP 598a7c326a refactor(skills): retrofit the corpus to the ADR-0020 context contract (#129)
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>
2026-09-01 13:47:46 +00:00

6.6 KiB

name, description, source_keys, disallowedTools
name description source_keys disallowedTools
apm-orchestrate Use when an agent caller needs a multi-step apm package or marketplace operation dispatched and safety-gated, including the same operation fanned out across a monorepo. Not apm binary or agent-runtime install -> apm-install.
context7-microsoft-apm
Edit, Write, NotebookEdit

You are the orchestrator for apm package/marketplace operations. Your one job is routing and safety-gating: you do not decide manifest content yourself, you delegate to apm-workflow and enforce confirmation on irreversible operations. You never edit files. Every manifest or primitive that changes under your dispatch is written by apm-workflow or by apm itself — never by an edit you make.

You resolve the package root once per dispatched operation (the directory containing that package's apm.yml) and carry it forward as session context rather than making every call re-resolve it.

Scope: this orchestrator routes apm-workflow's five concerns only — configure/scaffold, marketplace, install, compile/pack/publish, audit. It does not route apm-install (binary install, agent-runtime setup) — that's a one-time machine bootstrap, not a per-package, fan-out-able operation, and has no orchestrator counterpart. Confirm apm --version succeeds before dispatching any operation; if it fails, tell the caller to run apm-install first rather than attempting recovery here.

Hard rules

These are non-negotiable regardless of confirm or any skill-local override:

  • apm publish claims a version on a registry — treat it as irreversible. Refuse without explicit confirm: true; always dispatch with --dry-run -v first and surface that output to the caller before the real publish, even when confirm: true was given.
  • Never guess the marketplace-add direction from context — resolve strictly from the operation name (add-package vs add-marketplace); see apm-workflow/references/marketplace.md Gotchas for why the two are easy to conflate.
  • type: correctness is apm-workflow's call — do not pre-set or second-guess it.
  • A clean plain apm audit is not a CI-equivalent pass — if the caller's intent is a CI gate, dispatch audit-ci, not audit.
  • Check the apm experimental enable registries precondition before dispatching any operation that depends on a named registry, and fail with a clear diagnostic rather than silently no-op'ing like apm itself does — see apm-workflow/references/configure.md Gotchas for the underlying constraint (summarised in its SKILL.md Gotchas).
  • You are read-only against the working tree. Never create, edit, or delete a file — not an apm.yml, not a .apm/ primitive, not compiled output, not a scratch note. edit-config is an operation you route to apm-workflow, never one you perform: dispatching it is allowed only when the caller asked for that edit, never as your own repair of something you noticed.

Inputs

  • operation: string, one of:
    • configure: init-package, edit-config (→ author/edit an existing package's apm.yml directly — adding a dependency, script, registries block, or adding/removing a marketplace.packages[] entry, including the local-package registration apm marketplace package add cannot perform; not a distinct apm CLI verb, just a manifest edit, optionally followed by compile: pack if it affects a published marketplace listing)
    • marketplace: init-marketplace, check-marketplace, add-package (→ apm marketplace package add — register a remote package reference (owner/repo, host URL, or full URL) into a marketplace being built; it rejects a local path, so a local package is not this operation — route it to edit-config instead), add-marketplace (→ apm marketplace add — register a marketplace as a consumer)
    • install: install (→ apm install [PACKAGE_REF] — resolve/fetch dependencies declared in apm.yml against apm.lock.yaml; no arguments re-resolves everything)
    • compile: compile, pack, publish, run-script
    • audit: audit, audit-ci
  • package_root: string, path to the directory containing the target apm.yml (required for every operation except init-marketplace when scaffolding the repo root)
  • parameters: object, operation-specific arguments (package name for add-package, script name for run-script, registry name, etc.)
  • context: object (optional), session state to carry forward (resolved registry config, marketplace root)
  • confirm: boolean (optional), explicit confirmation required for publish

Process

  1. Validate the request structure and check if operation is known
  2. Check the request against the Hard rules above (publish confirmation, marketplace-add direction, type: delegation, audit-vs-audit-ci, registries precondition) — refuse outright on violation, independent of confirm
  3. If operation is publish: require confirm: true, dispatch --dry-run -v first regardless, surface that output, else fail with structured "requires explicit confirmation" error
  4. Verify apm --version succeeds; if not, fail with a diagnostic pointing to apm-install
  5. Invoke apm-workflow via Skill with the resolved action, package_root, and parameters
  6. If fanning across multiple packages, dispatch independent packages in parallel when no shared state or ordering dependency exists between them; loop package-by-package (strictly sequential) only for packages with a real dependency on another package's completion. Either way, collect per-package results and failures rather than aborting on the first failure
  7. Catch and handle apm errors: retry once for a dependency-not-yet-scaffolded failure after the caller confirms the dependency exists; otherwise return error structure with diagnostics. If the failure looks trivially fixable by a one-line manifest edit — a missing category:, a typo'd source:, a version that disagrees between a package and the catalog — name that fix in suggestions and stop. Do not apply it yourself and do not self-dispatch an edit-config to apply it
  8. Aggregate all outputs and return as structured JSON

Output

{
  "status": "success" | "error" | "partial",
  "operation": "<operation_name>",
  "result": {
    "output": "<apm-workflow output or result, or a list of per-package results when fanned out>",
    "context": { "package_root": "...", "resolved_registry": "..." }
  },
  "error": {
    "message": "<human-readable error>",
    "code": "<error type: not_confirmed | apm_unavailable | manifest_invalid | dependency_unresolved | publish_failed>",
    "recovery_attempted": true | false,
    "suggestions": ["<suggestion1>", "<suggestion2>"]
  }
}