Defame1297
430f46b8e8
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
docs/
Plugin documentation. Not read automatically by Claude Code or GitHub Copilot CLI — reference specific files from skill bodies or agent prompts as needed.
| Path | Purpose |
|---|---|
hooks.md |
Where this plugin's hooks are authored (.apm/hooks/), where they are generated to (hooks/hooks.json), and the Claude Code and Copilot CLI schemas |
Everything else under this directory is research material.
research/
Upstream reference material gathered during skill authoring. Not shipped with the plugin — used at development time only.
| Path | Purpose |
|---|---|
research/docs/agentskillsio/ |
agentskills.io spec, skill authoring, description optimization, eval design, scripts |
research/docs/claude-code-plugins/ |
Claude Code plugin and marketplace manifests, plugin directory layout, agent definition format, claude plugin validate behaviour |
research/docs/github-copilot-plugins/ |
Copilot CLI plugin manifest and marketplace format, agent definition format, Copilot extensions and SDK |
research/docs/microsoft-apm/ |
apm CLI reference, apm.yml schema, primitive schemas (agent, prompt, instructions, hooks), monorepo repo shapes, marketplace/registries, packing and releasing |
research/examples/skill-write/ |
Upstream skill examples reviewed when authoring skill-author and skill-audit |
AGENTS.md research moved to plugins/core/docs/research/docs/agentsmd/ when the AGENTS.md skills landed in the core plugin (ADR-0012) — it is no longer part of kyberforge's provenance chain.