Second clean-context audit found author Must/Should and audit FAIL/SUGGESTION tiers drifting apart, and author Musts the audit never checked. - factory-audit: FAIL on absolute or bare relative hook script paths, an applyTo present but empty, and unbalanced braces/brackets in applyTo; judgment steps for dependency stem collisions, helper .json in hook dirs, unresolvable instruction links, prompt model slugs and second-person bodies; an unmatched glob drops to SUGGESTION; deliberate tier deviations recorded in hook-flow.md; validate.sh --help lists the three new modes; DescriptionOpener message no longer prescribes "Use when". - primitive-author: deprecated routing, extra prompt keys and the prompt description contract become Shoulds; hook Musts gain "contributes an entry", no bare relative paths, and executable-when-run-directly; prompt Must 1 covers hardlinks; Vale prose FAILs resolved at close. - forge: say "hook, instruction or prompt" rather than "apm primitive". Refs #94 Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01KkT7RSDwDbmrM9T34b6sTi
4.7 KiB
4.7 KiB
source_keys
| source_keys | ||
|---|---|---|
|
Authoring an apm hook
Reached from SKILL.md Step 1 for a hook. Run the Gate, then write against the shape and the
checklist, then return to SKILL.md Step 3.
Gate
A hook is a runtime callback the harness fires inside its own tool loop — "this must always happen at this event", enforced deterministically rather than left to the model. apm's own guidance is to reach for a skill, instruction or prompt first, and to treat hooks as opt-in surface: they ship to a strict subset of harnesses and are silently skipped everywhere else.
- Procedure, know-how, or anything the model should decide to do → a skill. Stop and hand to
skill-author. - The hook must reach only some harnesses → reach is set by the package
apm.ymltargets:, never by the hook file. Stop and hand toapm-workflow.targets:is package-wide, so a harness-specific hook in a multi-target package means either a separate package or accepting that the other targets receive it too. - A runtime callback → continue.
Shape
One JSON file per concern at .apm/hooks/<name>.json, with a plain name. Copy
assets/templates/hook.json.template. Write the canonical shape apm documents and renders per
target:
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{"type": "command", "command": "${PLUGIN_ROOT}/.apm/hooks/check.sh", "timeout": 10}
]
}
]
}
}
${PLUGIN_ROOT}is the target-neutral token; apm rewrites it per target ("${CLAUDE_PROJECT_DIR}/.claude/hooks/<pkg>/…"on Claude, repo-relative elsewhere).${CLAUDE_PLUGIN_ROOT}is rewritten identically, so it is valid, but it ties the source to one harness's name (Should 12).- Claude is the verified target. apm 0.28.0 passes this nested shape to Copilot without
reshaping it, and whether Copilot CLI runs nested entries or honours
matcheris unverified. That gap is apm's to close. Per-file target routing is deprecated, so a Copilot-native flat hook (bash/powershell/timeoutSec) can only live in a separate Copilot-targeted package — hand that toapm-workflowrather than adding a second file here.
Checklist
Must:
- The file sits directly in
.apm/hooks/, is not a symlink, and parses as a JSON object. apm skips invalid JSON silently. (apm also discovers a package-roothooks/, andfactory-auditaccepts it for third-party packages; author in.apm/hooks/.) - Use the wrapped shape
{"hooks": {Event: [...]}}. If a naked settings slice is used instead, every top-level value must be a list, with no stray scalar keys anywhere. - Every event value is a list of objects, and every nested
hooksis a list of objects. Anything else fails the Copilot install outright. The file contributes at least one entry: an empty one deploys nothing, with only a warning. - Event names are PascalCase (
PreToolUse,PostToolUse,UserPromptSubmit,SessionStart,Stop, …). An all-lowercase name (stop) never warns and never fires; a camelCase name outside apm's rename map (userPromptSubmit) deploys verbatim to Claude and never fires. - The script is referenced as
${PLUGIN_ROOT}/…(or${CLAUDE_PLUGIN_ROOT}/…, see Shape) for the package root, or./…for the hook directory, and exists inside the package. No absolute path and no bare relative path (scripts/x.sh): apm bundles and rewrites neither. No$or backtick in the path itself. A missing script is only a warning at install time. - A script run directly as the command's first token is executable. This is stricter than the
research's Should: without it the hook fails every time it fires. A script passed to an
interpreter (
bash ${PLUGIN_ROOT}/x.sh) needs no executable bit.
Should:
- Every handler sets
"type": "command"and an explicittimeoutin seconds — apm passestypethrough but never supplies it. - Set
matcherexplicitly on tool events and onSessionStart(startup,resume, …). Omitted, Claude receives"*". - Do not author Copilot's flat
bash/powershell/timeoutSeckeys in a Claude-shaped file; they render onto Claude as stray keys. - Quote a script path that may contain spaces:
"${PLUGIN_ROOT}/scripts/my hook.sh". - Keep helper files in the hook directory non-JSON. Copilot's loader rejects any bundled
.jsonwithout ahookskey. - Prefer
${PLUGIN_ROOT}over${CLAUDE_PLUGIN_ROOT}. - No
hooks-<target>or*-<target>-hooksfilename. That routing is deprecated and reach belongs totargets:(see Gate); the research allows it only when deprecated routing is intended.