agentleFS
Sign inStart free
malinskibeniaminmalinskibeniamin/skills/extend-harness/SKILL.md

extend-harness

Skill4 starsChanged 11 days agoMITView on GitHub

Extend the harness: shell rules, Claude Code mods, severity tiers, and analytics.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Prefer Biome/Ultracite; hooks cover cross-element/file, workflow, agent behavior.

    line 17
  2. Very specific:

    Add focused evals/ fixture.

    line 20
  3. Very specific:

    Use hook_warn for style, hook_block correctness, hook_block_strict security, hook_info observation.

    line 28

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Edit manifests/libraries, not generated configs. REFERENCE.md: severities, options, parser contracts, debugging.

Claude mods: MODS.md. Cross-runtime enforcement stays in settings hooks.

Evidence bar

Compose existing skills before adding. Justify rules with a real failure or unmet contract; prove clean -> violation -> clean.

Add rule

  1. Prefer Biome/Ultracite; hooks cover cross-element/file, workflow, agent behavior.
  2. Copy .claude/hooks/checks/*.lib.sh: one run_* function and thin .claude/hooks/*.sh wrapper.
  3. Register in skill-manifest.json, usually PostToolUse.Edit|Write.
  4. Add focused evals/ fixture; prove RED -> GREEN.
  5. Regenerate and test:
bash scripts/generate-hook-configs.sh --apply
echo '{"hook_event_name":"PostToolUse","tool_name":"Edit","tool_input":{"file_path":"/tmp/x.ts"}}' | bash .claude/hooks/my-check.sh

Use hook_warn for style, hook_block correctness, hook_block_strict security, hook_info observation. Prefer skill-scoped hooks for one vertical.

Implementation

  • Manifest objects carry permission/async filters; retain stdin guards: Codex drops Claude-only filters.
  • Structure: Biome/AST; judgment: review.
  • Sync toolchain bans with hooks/frontend-skills.rules.

Audit/debug

/hook-audit --all: latency/firing/zero-fire; HOOK_DEBUG=1 HOOKS_FAIL_CLOSED=1 claude: missing hooks; claude --safe-mode: isolate customization. /doctor latency is a P95 budget failure.

Done

Manifest owns matcher; executable script sources _hook-lib.sh, parses stdin, filters paths, documents escape; fixture proves RED -> GREEN; generator --check and bash evals/run.sh pass.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free