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
provider-adapter-author
Convert a target repo's provider-specific instruction file (CLAUDE.md, .cursor/rules, copilot-instructions.md, etc.) into a thin adapter over AGENTS.md.
What it does
Detects a provider-specific AI instruction file in a target repo, diffs it against the repo's AGENTS.md, and rewrites it down to a minimal reference — an @AGENTS.md-style import for providers that support one, or a text pointer for those that don't — plus only genuinely provider-specific additions. Self-validates its own output with a bundled deterministic script (no LLM judgment, no separate audit skill) before finishing.
Before you start
The target repo must already have an AGENTS.md. If it doesn't, run agentsmd-author first — this skill never creates or edits AGENTS.md itself.
Usage
/provider-adapter-author
Provide the path to the provider-specific file to convert (and the target repo root, if not inferable). Can be invoked directly, or composed into by agentsmd-author when it detects an existing provider file with content overlapping AGENTS.md.
Files
| File | Purpose |
|---|---|
SKILL.md |
Skill instructions for agents |
references/sources.md |
Provenance record — the in-repo ADR precedent this skill's design is modeled on |
scripts/validate-adapter.sh |
Self-check gate: reference to AGENTS.md present, no excessive duplication, adapter stays thin |
scripts/README.md |
Directory documentation for scripts/ |
tests/README.md |
(source-only) Bats test dependency and run instructions |
tests/validate-adapter.bats |
(source-only) Bats test suite for scripts/validate-adapter.sh |
Rows marked (source-only) exist in the authoring source (.apm/skills/provider-adapter-author/)
but are not present in an installed plugin: scripts/sync-plugin-content.sh strips
<category>/<name>/tests when it generates the flat mirror, because these are dev-time fixtures no
plugin host needs to discover (ADR-0017). Run them from a repo checkout, not from an install.