agentleFS
Sign inStart free
zoranmarticzoranmartic/coord-wright/skills/coord-dirty/SKILL.md

coord-dirty

Skill0 starsChanged 47 days agoApache-2.0View on GitHub

Inspect coord project worktrees for dirty files and likely unfinished agent or worker ownership. Use when the user says /coord-dirty, asks which worktrees are dirty, asks what agent left files behind, or asks for dirty coord state across a project or all registered projects.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Read-only diagnostic for dirty coord worktrees.

    line 6
  2. Distinctive:

    Run the helper from the current directory unless the user asks otherwise:

    line 15
  3. Very specific:

    All registered projects: "${COORD_TOOLS:-$HOME/Projects/coord-wright}/bin/coord-dirty" --all-projects

    line 18
  4. Very specific:

    If output is long, show the head and tail with a [...

    line 23
  5. Very specific:

    Default scope is the current coord project.

    line 38
  6. Distinctive:

    Prefer the helper output over ad hoc git commands unless the helper itself is missing or fails.

    line 40

≈ “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

Read-only diagnostic for dirty coord worktrees. Do not mutate files, task state, commits, branches, or launchd services from this skill.

Syntax

/coord-dirty [--project <name-or-path>] [--all-projects] [--json]

Workflow

  1. Run the helper from the current directory unless the user asks otherwise:
    • Current project: "${COORD_TOOLS:-$HOME/Projects/coord-wright}/bin/coord-dirty"
    • One project: "${COORD_TOOLS:-$HOME/Projects/coord-wright}/bin/coord-dirty" --project <name-or-path>
    • All registered projects: "${COORD_TOOLS:-$HOME/Projects/coord-wright}/bin/coord-dirty" --all-projects
    • Machine-readable output: add --json
  2. Report the helper output plainly. Preserve the distinction between proven state and likely_owner; likely ownership is a heuristic from task status, worker locks, worker logs, branch names, and dirty status.
  3. If output is long, show the head and tail with a [... N lines truncated ...] marker and always keep FAIL/WARN lines. Summarize by project, keeping dirty worktree rows and worker hints. Do not hide helper errors.

Interpretation

  • coord worker active means the project worker lock PID is currently alive.
  • codex on <task> or claude on <task> comes from a *-working task status.
  • latest worker run comes from .coord/worker.log; it is a recent hint, not proof that the agent owns all current dirty files.
  • pre-existing before <agent> means the worker logged that the checkout was already dirty before that agent started.
  • manual/task branch and manual task worktree are branch/path heuristics.

Rules

  • Read-only only.
  • Default scope is the current coord project. Use --all-projects only when the user explicitly asks for all repos/projects/worktrees.
  • Prefer the helper output over ad hoc git commands unless the helper itself is missing or fails.

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