agentleFS
openclosed-orgopenclosed-org/axum-harness/.agents/skills/harness-grill/SKILL.md

harness-grill

Skill48 starsChanged 6 months agoApache-2.0View on GitHub

Alignment workflow for ambiguous harness plans, architecture choices, scope, and terminology. Use when requirements are fuzzy, terms are overloaded, a decision affects multiple ownership boundaries, or the user asks to stress-test a plan before implementation.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to reach shared understanding before code or docs change.

    line 11
  2. Very specific:

    Read AGENTS.md, agent/codemap.yml, docs/architecture/north-star.md, and docs/architecture/harness-philosophy.md.

    line 17
  3. Very specific:

    Use declared, checked, tested, and proven precisely.

    line 21
  4. Very specific:

    If user wording conflicts with AGENTS.md, agent/codemap.yml, accepted ADRs, or executable evidence, call out the conflict directly.

    line 27
  5. Distinctive:

    If a claim conflicts with executable evidence, surface the mismatch and ask which should change.

    line 28
  6. Distinctive:

    If the plan mixes current state, target state, file maps, and roadmap, recommend splitting before implementation.

    line 29
  7. Distinctive:

    If optional lanes are becoming backend-core prerequisites, flag drift.

    line 30
  8. Distinctive:

    Stop when the next implementation step, owner boundary, evidence expectation, and out-of-scope set are clear enough to hand to an ownership …

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Harness Grill

Use this skill to reach shared understanding before code or docs change.

Workflow skills guide process. Ownership skills still decide writable boundaries.

Process

  1. Read AGENTS.md, agent/codemap.yml, docs/architecture/north-star.md, and docs/architecture/harness-philosophy.md.
  2. Explore executable sources when they can answer the question. Do not ask the user to restate facts the codebase can show.
  3. Walk the decision tree one question at a time.
  4. For each question, provide your recommended answer and why.
  5. Use declared, checked, tested, and proven precisely.
  6. Record unresolved vocabulary in docs/_local/** only when useful, without promoting it into tracked docs by default.
  7. Offer an ADR only when the decision is hard to reverse, surprising without context, and a real trade-off.

Challenge Rules

  1. If user wording conflicts with AGENTS.md, agent/codemap.yml, accepted ADRs, or executable evidence, call out the conflict directly.
  2. If a claim conflicts with executable evidence, surface the mismatch and ask which should change.
  3. If the plan mixes current state, target state, file maps, and roadmap, recommend splitting before implementation.
  4. If optional lanes are becoming backend-core prerequisites, flag drift.

Stop Condition

Stop when the next implementation step, owner boundary, evidence expectation, and out-of-scope set are clear enough to hand to an ownership skill or agent brief.

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.