cancel
Cancel any active execution mode — stops autopilot, ralph, ultrawork, team, ultraqa cleanly
Skill by TheTrustedAdvisor
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/thetrustedadvisor-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
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 execution mode — stops autopilot, ralph, ultrawork, team, ultraqa cleanly
- License
- MIT
- Instructions
- 104 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
## When to Use
- User wants to stop an active execution mode
- User says "cancel", "stop", "abort", "cancelomc"
- Work is complete and mode needs clean exit
- Mode is stuck and needs forced termination
## What It Cancels
| Mode | Cancel Behavior | State Preserved |
|------|----------------|-----------------|
| **autopilot** | Stop current phase | `.omg/qa-logs/autopilot-*` |
| **ralph** | Stop persistence loop | `.omg/qa-logs/ralph-prd.json`, `ralph-progress.md` |
| **ultrawork** | Stop parallel execution | Wait for in-flight tasks |
| **ultraqa** | Stop QA cycling | `.omg/qa-logs/ultraqa-log.md` |
| **team** | Shutdown workers | `.omg/qa-logs/team-log.md` |
## Workflow
### 1. Detect Active Mode
Check for active state files:
```bash
ls .omg/qa-logs/*-prd.json .omg/qa-logs/*-state.json .omg/qa-logs/*-log.md 2>/dev/null
```
Also check `store_memory` for active mode keys (`omg:active-plan`, etc.).
### 2. Preserve State
Before cancelling, ensure current progress is saved:
| Mode | What to Save | Where |
|------|-------------|-------|
| Ralph | Current PRD (which stories passed) | `.omg/qa-logs/ralph-prd.json` |
| Autopilot | Current phase + completed phases | `.omg/qa-logs/autopilot-state.json` |
| Team | Subtask completion status | `.omg/qa-logs/team-log.md` |
| UltraQA | Cycle count + last error | `.omg/qa-logs/ultraqa-log.md` |
### 3. Clean Exit
- Wait for in-flight `task(background)` agents to complete (best effort, 30s timeout)
- Report what was completed and what remains
- State files preserved for resume (NOT deleted)
### 4. Report
```
## Cancel Report
Mode: {mode}
Status: CANCELLED
### Completed
- {what was done}
### Remaining
- {what's left}
### Resume
To resume: re-invoke the mode. It will read state from .omg/qa-logs/ and continue.
```
### 5. Force Cancel
If normal cancel fails (stuck agents, unresponsive):
```bash
# Remove state files to unblock
rm -f .omg/qa-logs/{mode}-state.json
```
Report force-cancel with warning about potential incomplete state.
## Resume After Cancel
Modes check `.omg/qa-logs/` on startup:
- **Ralph:** reads `ralph-prd.json`, skips completed stories
- **Autopilot:** reads phase state, resumes from last phase
- **Team:** reads team log, re-assigns incomplete subtasks
- **UltraQA:** reads cycle log, continues from last cycle
## Checklist
- [ ] Active mode detected
- [ ] Progress preserved before exit
- [ ] In-flight agents given time to complete
- [ ] Clean shutdown reported
- [ ] State preserved for resume
## Trigger Keywords
cancel, stop, abort, cancelomc
## Example
```bash
copilot -i "cancelomc"
```
## Quality Contract
- Clean shutdown, preserves stateFrom TheTrustedAdvisor/omg, MIT.
More from TheTrustedAdvisor/omg
- 0.466score
btw
TheTrustedAdvisor
Quick side-question without derailing the current task — answers in a separate context to keep the main conversation clean
SkillDFreshness: D★ 7Claude Code +9 - 0.463score
agent-catalog
TheTrustedAdvisor
Agent directory — lists all omg agents with their roles, models, and when to use each
SkillDFreshness: D★ 7Claude Code +9 - 0.463score
ai-prose-cleaner
TheTrustedAdvisor
Detect and clean AI-typical writing patterns in documents — em dashes, filler phrases, over-formality
SkillDFreshness: D★ 7Claude Code +9 - 0.463score
ai-slop-cleaner
TheTrustedAdvisor
Clean AI-generated code — remove unnecessary abstractions, verbose comments, over-engineering
SkillDFreshness: D★ 7Claude Code +9 - 0.463score
ask
TheTrustedAdvisor
Route questions to Claude, Codex, or Gemini for multi-perspective answers
SkillDFreshness: D★ 7Claude Code +9 - 0.463score
autopilot
TheTrustedAdvisor
Activates full autonomous execution — from idea to working, verified code
SkillDFreshness: D★ 7Claude Code +9 - 0.463score
ccg
TheTrustedAdvisor
Claude-Codex-Gemini tri-model orchestration — decompose, query, synthesize
SkillDFreshness: D★ 7Claude Code +9 - 0.463score
configure-notifications
TheTrustedAdvisor
Set up notification integrations — Telegram, Discord, Slack alerts for long-running tasks
SkillDFreshness: D★ 7Claude Code +9 - 0.463score
debug
TheTrustedAdvisor
Structured debugging — reproduce, diagnose, fix with @omg:debugger agent
SkillDFreshness: D★ 7Claude Code +9 - 0.463score
deep-analyze
TheTrustedAdvisor
Deep analysis mode — multi-agent investigation of complex systems or problems
SkillDFreshness: D★ 7Claude Code +9 - 0.463score
deep-dive
TheTrustedAdvisor
Activates investigation-to-requirements pipeline — trace root cause then crystallize into actionable spec
SkillDFreshness: D★ 7Claude Code +9 - 0.463score
deep-interview
TheTrustedAdvisor
Socratic deep interview with ambiguity scoring — crystallize vague ideas into clear specs before execution
SkillDFreshness: D★ 7Claude Code +9
Signals
- Stars
- 7
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Apr 8, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/TheTrustedAdvisor/omg
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from TheTrustedAdvisor
- 0.466score
btw
TheTrustedAdvisor
Quick side-question without derailing the current task — answers in a separate context to keep the main conversation clean
SkillDFreshness: D★ 7Claude Code +9 - 0.463score
ai-prose-cleaner
TheTrustedAdvisor
Detect and clean AI-typical writing patterns in documents — em dashes, filler phrases, over-formality
SkillDFreshness: D★ 7Claude Code +9 - 0.463score
ai-slop-cleaner
TheTrustedAdvisor
Clean AI-generated code — remove unnecessary abstractions, verbose comments, over-engineering
SkillDFreshness: D★ 7Claude Code +9 - 0.463score
ask
TheTrustedAdvisor
Route questions to Claude, Codex, or Gemini for multi-perspective answers
SkillDFreshness: D★ 7Claude Code +9 - 0.463score
autopilot
TheTrustedAdvisor
Activates full autonomous execution — from idea to working, verified code
SkillDFreshness: D★ 7Claude Code +9 - 0.463score
agent-catalog
TheTrustedAdvisor
Agent directory — lists all omg agents with their roles, models, and when to use each
SkillDFreshness: D★ 7Claude Code +9
Cite this page
cancel skill. Agent Mart. https://agentmart.dev/skills/thetrustedadvisor-cancel (last updated 2026-10-24)