agentleFS
zoranmarticzoranmartic/coord-wright/skills/coord-discard/SKILL.md

coord-discard

Skill0 starsChanged 47 days agoApache-2.0View on GitHub

Abandon a coord task you no longer want. Marks it `done` with a discard note; `coord update` archives it in the same call. Use when the user says "/coord-discard", "drop <id>", "kill <id>", or "abandon <id>".

  • Commits and pushes

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    If already done: report and stop.

    line 22
  2. Very specific:

    If a non-forced close is refused for incomplete subtasks, stop and report.

    line 33
  3. Very specific:

    Never edit task files directly.

    line 42
  4. Very specific:

    Never run manual git add, git commit, or git push — coord update auto-commits-and-pushes each mutation.

    line 43

≈ “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

Cancel a coord task without finishing it. coord update --status=done moves the file to the configured archive directory in the same call.

Project-root preflight:

  • Resolve the canonical project checkout before reading, updating, staging, committing, or pushing: 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; discard must update the main queue that the launchd worker reads.

Syntax

/coord-discard <task-id> [--reason="..."]

Workflow

  1. Read current state.
    • python3 "${COORD_TOOLS:-$HOME/Projects/coord-wright}/bin/coord" show <id> → confirm task exists and is not already done.
    • If already done: report and stop; it is already archived.
  2. Compose the discard note.
    • Reason: from --reason="..." if supplied, else discarded by user.
    • Note text: Discarded <ISO-timestamp>: <reason> (use date +%Y-%m-%dT%H:%M:%S%z, local time with explicit offset).
  3. Append the note and mark done in one call (no partial state if the status change is refused).
    • From claude-working, codex-working, or needs-review: python3 "${COORD_TOOLS:-$HOME/Projects/coord-wright}/bin/coord" update <id> --status=done --add-issues="<note>"
    • From shaping, pending, or needs-brainstorming: the transition table has no edge to done, so the same command needs --force. The /coord-discard invocation is the user's explicit request to abandon the task; add --force to the command above.
    • Quote the note (it contains spaces). --add-issues puts it under ## Open issues, preserved in the archive.
    • If a non-forced close is refused for incomplete subtasks, stop and report; use --force only after the user confirms the subtasks are intentionally abandoned.
    • coord update auto-commits-and-pushes. Do not run any manual git add, git commit, or git push.
  4. Report.
    • discarded: <id> — already moved to the configured archive directory.
    • Confirm with python3 "${COORD_TOOLS:-$HOME/Projects/coord-wright}/bin/coord" show <id> that status: done is written.

Rules

  • Never edit task files directly; always go through coord update.
  • Never run manual git add, git commit, or git push — coord update auto-commits-and-pushes each mutation.
  • --force only for the no-edge sources above or with explicit user confirmation that incomplete subtasks are intentionally abandoned.
  • Never use --no-verify.
  • Archiving is part of coord update --status=done; there is no separate archive step.

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.