agentleFS
igovetigovet/cortex-orch-acp/skills/tool-discipline-worker/SKILL.md

tool-discipline-worker

Skill1 starsChanged 59 days agoMITView on GitHub

Worker-only project scope and reportable command evidence.

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. Very specific:

    Before changing additional project paths, reserve them through access_request.

    line 9
  2. Distinctive:

    Use scope or replan requests only when the plan itself must change.

    line 13
  3. Very specific:

    Run reportable checks through Cortex MCP command_run or its approved outside route and retain terminal receipts for the structured result.

    line 15

≈ “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

Worker tool discipline

Declared scope coordinates parallel writers; it is not a project write boundary. Before changing additional project paths, reserve them through access_request. Private storage and user-protected paths remain unavailable. Outside-project work uses the advertised permission route and follows the user's current mode. A denied action is final; never substitute a native tool, copy or temporary file. Use scope or replan requests only when the plan itself must change.

Run reportable checks through Cortex MCP command_run or its approved outside route and retain terminal receipts for the structured result. Native workspace aids, where permitted, do not produce Cortex command evidence. Writing workers verify edits; read-only workers run only authorized non-mutating checks. Scope diff/whitespace checks to owned paths. Retain and attribute sibling-owned failures separately; never call them passed or abandon otherwise verified work.

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.