cancel
Cancel any active OMX mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team)
Skill by Yeachan-Heo
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/yeachan-heo-cancel
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: data, agent-building, agent-orchestration
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/cancel
What's inside
- Skill name
cancel- Description
- Cancel any active OMX mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team)
- License
- MIT
- Instructions
- 37 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Cancel Skill
## When to use
Use `/cancel` (or `cancelomc` / `stopomc`) to stop an active OMX mode and perform its documented cleanup. Read `AGENTS.md#durable-runtime-invariants-canonical-ssot` first; it is the invariant authority for scope, ownership, hooks, and Team cleanup.
## Inputs and preconditions
- Accepted forms are `/cancel` and `/cancel --force`.
- Reject `--all`, unknown flags, repeated flags, and mixed flags before mutation.
- Discover the current session/root with the state read surfaces before cleanup:
```bash
omx state list-active --json
omx state get-status --mode <mode> --json
```
- Confirm the current session/root and exact target before cleanup; stop when the required evidence is missing.
## Operational steps
1. Parse and validate arguments; select one exact session/root scope.
2. Inspect active modes in dependency order:
`autopilot → ralph → ultrawork → ecomode → ultraqa → swarm → ultrapilot → pipeline → team → plan-consensus`.
3. Cancel Autopilot while preserving its resumable state; clean only linked child modes it owns.
4. For Ralph, terminalize the target state (`active:false`, `current_phase:"cancelled"`, `completed_at`) and terminalize a proven linked Ultrawork/Ecomode state in the same scope. Confirm the post-conditions in `docs/contracts/ralph-cancel-contract.md`.
5. Clear standalone modes only after proving they are not linked to another active mode.
6. For Team, inspect the runtime with `omx team status <team> --json`; use `omx team shutdown <team>` after the normal completion gate, or follow the explicit abort path.
7. Clear only the selected mode/session state through the state API, for example:
```bash
omx state clear --input '{"mode":"<mode>","session_id":"<session>"}' --json
```
8. With `--force`, perform its documented native-stop cleanup. Report rollback or cleanup failures rather than claiming success.
## Exit and evidence
Report one result per selected mode: mode, scope/session, terminal phase, preserved state, linked cleanup, and any refusal reason. A clean no-op reports `No active OMX modes detected.` Include Team status and shutdown evidence when Team was selected.From Yeachan-Heo/oh-my-codex, MIT.
More from Yeachan-Heo/oh-my-codex
- 0.849score
performance-goal
Yeachan-Heo
Run an evaluator-gated performance optimization workflow over Codex goal mode with durable OMX artifacts and safe goal handoffs.
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.847score
analyze
Yeachan-Heo
Run read-only deep repository analysis and return a ranked synthesis with explicit confidence, concrete file references, and clear evidence-vs-inference…
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
ask
Yeachan-Heo
Ask a local external advisor CLI (Claude or Gemini) and capture a reusable artifact
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
wiki
Yeachan-Heo
Persistent markdown project wiki stored under repository omx_wiki with keyword search and lifecycle capture
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
autoresearch
Yeachan-Heo
Stateful validator-gated research loop with native-hook persistence
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
best-practice-research
Yeachan-Heo
[OMX] Bounded best-practice research wrapper using official/upstream evidence first
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
ultragoal
Yeachan-Heo
Create and execute durable repo-native multi-goal plans over Codex goal mode artifacts.
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
git-master
Yeachan-Heo
Git expert for atomic commits, rebasing, and history management
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
autopilot
Yeachan-Heo
[OMX] Canonical autonomous orchestrator: $deep-interview -> $ralplan -> $ultragoal
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
worker
Yeachan-Heo
Team worker protocol (ACK, mailbox, task lifecycle) for tmux-based OMX teams
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.844score
visual-ralph
Yeachan-Heo
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict…
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.842score
hud
Yeachan-Heo
Show or configure the OMX HUD (two-layer statusline)
SkillAFreshness: A★ 33.6KClaude Code +9
Signals
- Stars
- 33,621
- Forks
- 2,549
- Open issues
- 1
- Last commit (this folder)
- Aug 12, 2026 (2 months ago)
- Last release
- Oct 24, 2026 (3 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Yeachan-Heo/oh-my-codex
- Website
- oh-my-codex.dev
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.441score
cancel
Yeachan-Heo
Cancel any active OMX mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team)
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.278score
cancel
Ciward
Cancel any active OMX mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team)
SkillCFreshness: CClaude Code +9 - 0.242score
cancel
ErenYegar
Cancel any active OMX mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team)
SkillDFreshness: DClaude Code +9 - 0.242score
cancel
pubgo
Cancel any active OMX mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team)
SkillDFreshness: DClaude Code +9 - 0.239score
cancel
krisadas
Cancel any active OMX mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team)
SkillDFreshness: DClaude Code +9 - 0.239score
cancel
gtpgg1013
Cancel any active OMX mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team)
SkillDFreshness: DClaude Code +9 - 0.239score
cancel
ChatGPT-KB
Cancel any active OMX mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team)
SkillDFreshness: DClaude Code +9 - 0.239score
cancel
pextacy
Cancel any active OMX mode (autopilot, ralph, ultrawork, ecomode, ultraqa, swarm, ultrapilot, pipeline, team)
SkillDFreshness: DClaude Code +9
More from Yeachan-Heo
- 0.849score
performance-goal
Yeachan-Heo
Run an evaluator-gated performance optimization workflow over Codex goal mode with durable OMX artifacts and safe goal handoffs.
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.847score
analyze
Yeachan-Heo
Run read-only deep repository analysis and return a ranked synthesis with explicit confidence, concrete file references, and clear evidence-vs-inference…
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
git-master
Yeachan-Heo
Git expert for atomic commits, rebasing, and history management
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
autoresearch
Yeachan-Heo
Stateful validator-gated research loop with native-hook persistence
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
best-practice-research
Yeachan-Heo
[OMX] Bounded best-practice research wrapper using official/upstream evidence first
SkillAFreshness: A★ 33.6KClaude Code +9 - 0.845score
ultragoal
Yeachan-Heo
Create and execute durable repo-native multi-goal plans over Codex goal mode artifacts.
SkillAFreshness: A★ 33.6KClaude Code +9
Cite this page
cancel skill. Agent Mart. https://agentmart.dev/skills/yeachan-heo-cancel (last updated 2026-10-24)