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

coord-status

Skill0 starsChanged 47 days agoApache-2.0View on GitHub

Show coord queue status, list tasks, display a specific task, or summarize a task result/outcome. Use when the user asks about coord state (\"what's pending\", \"show task X\", \"show result for X\", \"coord status\", \"any tasks waiting\").

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read-only view onto the shared coord queue.

    line 6
  2. Distinctive:

    Use this for operator review of a completed or near-completed task.

    line 23
  3. Very specific:

    Do not use it as a worker startup packet.

    line 24
  4. Very specific:

    Follow up with a list if the user wants the full table.

    line 39
  5. Very specific:

    Never mutate state from this skill.

    line 44
  6. Very specific:

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

    line 45

≈ “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 view onto the shared coord queue. Does not modify task state.

Source of truth:

  • ${COORD_TOOLS:-$HOME/Projects/coord-wright}/docs/architecture.md
  • ${COORD_TOOLS:-$HOME/Projects/coord-wright}/docs/task-files.md

Project-root preflight:

  • Resolve the canonical project checkout before any coord command: COORD_MAIN=$("${COORD_TOOLS:-$HOME/Projects/coord-wright}/bin/coord-project-root") && cd "$COORD_MAIN"
  • This is required when the skill is invoked from a sibling task worktree; status must reflect the main queue that the launchd worker reads.

Dispatch (pick the narrowest that matches the user's ask):

  1. Specific task result / outcome (e.g. "show result for <id>", "what happened in <id>", "finished evidence for <id>", "outcome of <id>"):
    • python3 "${COORD_TOOLS:-$HOME/Projects/coord-wright}/bin/coord" show <id> --result
    • Use this for operator review of a completed or near-completed task. It is a compact read-only view over persisted task state: handoff header, latest terminal finding, final handoff content when present, and token total when available.
    • Do not use it as a worker startup packet; active rounds still use show <id> --handoff.
  2. Specific task id (e.g. "show 2026-05-02-foo", "what's in <id>"):
    • python3 "${COORD_TOOLS:-$HOME/Projects/coord-wright}/bin/coord" show <id> --compact
    • Escalate to show <id> --handoff or full show <id> only if the user wants more detail.
  3. Filtered list (e.g. "what's pending for claude", "show codex tasks", "anything blocked"):
    • python3 "${COORD_TOOLS:-$HOME/Projects/coord-wright}/bin/coord" list --status=<csv> --assigned=<csv>
    • Common filters:
      • Pending Claude work: --status=pending,needs-review --assigned=claude
      • Pending Codex work: --status=pending,needs-review --assigned=codex
      • Stuck / needs triage: --status=needs-brainstorming
  4. Operator overview (default for "coord status", "what's the state of the loop"):
    • python3 "${COORD_TOOLS:-$HOME/Projects/coord-wright}/bin/coord" status
    • Follow up with a list if the user wants the full table.
    • The output appends a soft warning when the last 3 completed tasks were all additive (no kind: code-cut, no negative scope_budget band). This is a sprint-level nudge toward the subtraction-as-opening-move policy in ${COORD_TOOLS:-$HOME/Projects/coord-wright}/docs/agent-workflow-policy.md. Surface the warning to the user — do not strip it. It is advisory, not a block; the shaper still decides.

Rules:

  • Never mutate state from this skill. For pickup/work, defer to coord-check. For new tasks, defer to coord-shape.
  • If output is long, show the head and tail with a [... N lines truncated ...] marker and always keep FAIL/WARN lines.
  • Report results plainly; do not fabricate task ids or statuses if the CLI returns nothing.

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