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

harness-diagnose

Skill48 starsChanged 6 months agoApache-2.0View on GitHub

Disciplined diagnosis workflow for failing gates, regressions, flaky behavior, performance regressions, and suspicious backend/runtime behavior. Use when the user reports a bug, broken invariant, failing command, failing test, or asks to diagnose/debug a problem.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill for bugs and regressions.

    line 11
  2. Distinctive:

    Add regression evidence at the same semantic level.

    line 22
  3. Very specific:

    Run path-scoped gates from agent/manifests/gate-matrix.yml.

    line 23
  4. Distinctive:

    Prefer fast, deterministic, agent-runnable signals:

    line 28
  5. Distinctive:

    If no credible loop can be built, stop and state what was tried and what artifact is needed.

    line 38
  6. Distinctive:

    Every probe must test one hypothesis.

    line 42
  7. Distinctive:

    Prefer debugger, targeted assertion, or narrow logs over broad logging.

    line 43

≈ “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 Diagnose

Use this skill for bugs and regressions.

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

Phases

  1. Build a feedback loop.
  2. Reproduce the exact symptom.
  3. Generate 3-5 ranked falsifiable hypotheses.
  4. Instrument one boundary or variable at a time.
  5. Fix the smallest causal closed loop.
  6. Add regression evidence at the same semantic level.
  7. Run path-scoped gates from agent/manifests/gate-matrix.yml.
  8. Report evidence and residual uncertainty.

Feedback Loop Options

Prefer fast, deterministic, agent-runnable signals:

  1. failing unit, service, integration, replay, or contract test
  2. validator or gate command
  3. CLI invocation with fixture input and expected output
  4. HTTP request against a running server
  5. replayed event, outbox, or projector trace
  6. throwaway harness isolated to one service, server, worker, or repo-tool path
  7. stress loop for flakes or concurrency issues

If no credible loop can be built, stop and state what was tried and what artifact is needed.

Instrumentation Rules

  1. Every probe must test one hypothesis.
  2. Prefer debugger, targeted assertion, or narrow logs over broad logging.
  3. Tag temporary logs with a unique prefix and remove them before completion.
  4. For performance regressions, measure first and fix second.

Completion Report

State:

  1. violated invariant
  2. causal boundary: contract, service, server, worker, platform, tooling, docs, or cross-boundary
  3. repair made
  4. regression evidence added or why no correct seam exists
  5. gates run
  6. gates not run
  7. residual risk or uncertainty

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.