agentleFS
YomudoglyYomudogly/oh-my-agy/skills/cancel/SKILL.md

cancel

Skill4 starsChanged todayMITView on GitHub

[oh-my-agy] Cancel active oh-my-agy workflow modes (autopilot, deep-interview, ralplan, plan, ultragoal, ultraqa, autoresearch, performance-goal, team) with exact-scope cleanup of their state, subagents, and background tasks. Use for $cancel, 'stop the workflow', 'cancel autopilot', or when a hard blocker prevents progress.

13 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use ultrawork, ralph and 4 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • zephyrpersonalSkill

    ultrawork

    Obsessive task completion mode (Sisyphus Mode) - activates maximum intensity work with todo continuation enforcement

    Also in 5 projects that use this

  • snarktankSkill

    ralph

    Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.

    Also in 7 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 4 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 4 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 3 projects that use this

  • GoogleSkill

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 0

    Distinctive

    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. Very specific:

    Use $cancel to stop an active oh-my-agy mode and run its documented cleanup: when work is verified done, the user says stop, or a hard …

    line 10
  2. Very specific:

    Autopilot: write active:false, current_phase:"cancelled", completed_at.

    line 24
  3. Very specific:

    Ultraqa: stop its background commands (manage_task list -> kill the ones it started), remove its temporary harnesses/fixtures, and …

    line 26

“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “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 Skill

When to use

Use $cancel to stop an active oh-my-agy mode and run its documented cleanup: when work is verified done, the user says stop, or a hard blocker prevents meaningful progress. Do not cancel while recoverable work remains unless the user asks.

Inputs and preconditions

  • Accepted forms: $cancel, $cancel <mode>, $cancel --force.
  • Reject --all, unknown flags, and repeated or mixed flags before changing anything.
  • Discover active modes by reading .omagy/state/*-state.json in the workspace root. Active means active:true and a non-terminal current_phase.
  • Confirm the exact target before cleanup. If several modes are active and no mode was named, cancel in dependency order (below) and report each one.

Operational steps

  1. Validate arguments and select the exact target mode(s).
  2. Process active modes in dependency order: autopilot -> team -> ultragoal -> ultraqa -> autoresearch -> performance-goal -> ralplan -> deep-interview -> plan.
  3. Autopilot: write active:false, current_phase:"cancelled", completed_at. Preserve handoff_artifacts and the iteration so a new $autopilot can resume from them. Clean up only the child work Autopilot owns (its team run, its ultraqa harnesses).
  4. Team (with worktree/branch preservation): manage_subagents list, then inspect only the conversation IDs recorded on .omagy/state/team/<team>/tasks.json. Because manage_subagents kill deletes branched workspaces, if any worker ran with Workspace: "branch" or "share" and has unmerged work, salvage or checkpoint its commits/branch in the leader lane first (stopping a worker is not permission to discard unsaved work). Then kill only those recorded worker conversation IDs, mark the remaining in_progress tasks blocked with result:"cancelled", and terminalize team-state.json. Never use kill_all unless the user explicitly aborts everything.
  5. Ultraqa: stop its background commands (manage_task list -> kill the ones it started), remove its temporary harnesses/fixtures, and terminalize its state.
  6. Ultragoal / performance-goal / autoresearch ($deep-research --loop state): terminalize the state file. Do not modify goals.json, the ledger, or evidence artifacts beyond appending one cancelled ledger note.
  7. Planning modes (ralplan, deep-interview, and plan written by $ralplan --light): terminalize the state. Keep the context snapshots, specs, and plans.
  8. --force: additionally delete the target mode's *-state.json file (exact path only) after terminalizing it. This is for corrupt or stale state that keeps the Stop hook nudging. It never widens scope.
  9. Report any cleanup failure instead of claiming success.

Terminal write shape (read-modify-write the existing file):

{"active": false, "current_phase": "cancelled", "completed_at": "<ISO>", "updated_at": "<ISO>", "cancel_reason": "<user request | blocker>"}

Exit and evidence

Report one line per selected mode: mode, terminal phase, what was preserved, linked cleanup (subagents killed, tasks stopped, files removed), and any refusal reason. A clean no-op reports No active oh-my-agy modes detected. When reporting checked missing-state paths on a no-op, limit the output to the current conversation's session paths (or cap checked paths at 10 with ... and N more checked paths).

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.