agentleFS
Sign inStart free
joinwell52-AIjoinwell52-AI/CodeFlowMu-open/skills/run-local-command-check/SKILL.md

run-local-command-check

Skill2 starsChanged 4 months agoMITView on GitHub

Use when an agent needs to run a local command for verification, diagnostics, tests, builds, typechecks, scripts, or CLI behavior and must report truthful command evidence.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use before running commands that produce evidence for a task, especially tests, typechecks, builds, local scripts, CLI diagnostics, or …

    line 10
  2. Distinctive:

    Prefer the smallest command that verifies the claim.

    line 16
  3. Distinctive:

    Run commands from the correct workspace directory.

    line 17
  4. Distinctive:

    Treat failure output as evidence, not as something to hide.

    line 19
  5. Distinctive:

    Do not claim success if a command failed or was not run.

    line 20
  6. Distinctive:

    Avoid destructive commands unless the task explicitly authorizes them.

    line 21
  7. Distinctive:

    Do not fabricate command output.

    line 35
  8. Distinctive:

    Do not run broad or slow checks when a narrow check is enough unless risk justifies it.

    line 36
  9. Distinctive:

    Do not use command success alone as proof of UI or product correctness when browser or manual behavior matters.

    line 37

≈ “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

Run Local Command Check

When to use

Use before running commands that produce evidence for a task, especially tests, typechecks, builds, local scripts, CLI diagnostics, or health checks.

Rules

  • State the command purpose before relying on its output.
  • Prefer the smallest command that verifies the claim.
  • Run commands from the correct workspace directory.
  • Capture the command, exit status, and key output.
  • Treat failure output as evidence, not as something to hide.
  • Do not claim success if a command failed or was not run.
  • Avoid destructive commands unless the task explicitly authorizes them.

Required output

When reporting, include:

  • Command.
  • Working directory.
  • Result: pass, fail, skipped, or blocked.
  • Key output lines or a concise summary.
  • Any follow-up risk from skipped checks.

Forbidden actions

  • Do not fabricate command output.
  • Do not run broad or slow checks when a narrow check is enough unless risk justifies it.
  • Do not use command success alone as proof of UI or product correctness when browser or manual behavior matters.

Minimal example

Command: npm --prefix packages/codeflowmu-runtime test
Purpose: verify runtime unit tests after router change
Result: pass
Evidence: 280 tests passed, 0 failed

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