Agent skill

OMG Mode Canceller

by zereight in zereight/gitlab-mcp

Detects which autonomous OMG mode is currently active - Autopilot, Ralph, Ultrawork, UltraQA, Team or Self-Improve - and shuts it down cleanly.

MITAuto-check passedAgent Workflows

Install OMG Mode Canceller

skills CLI
$ npx skills add zereight/gitlab-mcp --skill cancel -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install zereight/gitlab-mcp cancel --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/zereight/gitlab-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/cancel .claude/skills/cancel && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cancel
GitHub stars
2k
Used in
1 other repo
Token cost
~690 tokens
SKILL.md length
317 words
Files
1
Skills in repo
24
Repo updated
First seen
Licence
MIT

At a glance

Detects which autonomous OMG mode is currently active - Autopilot, Ralph, Ultrawork, UltraQA, Team or Self-Improve - and shuts it down cleanly.

  • Works in 2 steps: Parse Arguments → Detect Active Modes
  • Stopping whichever autonomous mode is currently running
  • SKILL.md covers What It Does, Usage, Auto-Detection and Workflow, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

This skill reads a local state folder to work out which of several autonomous modes is currently running, then cancels it in a dependency-aware order: OMG Autopilot first (including any linked Ralph or UltraQA cleanup), then a standalone Ralph loop, Ultrawork, UltraQA, a running Team, and finally a Self-Improve loop. A force flag skips detection and clears every state file outright.

Depending on the mode, cancellation either preserves state for a later resume - OMG Autopilot keeps its phase, files and spec, and Self-Improve keeps its iteration count - or clears the state entirely, as with Ralph, Ultrawork and UltraQA, and a Team shutdown, which signals every teammate and waits up to 15 seconds per member for a response before cleaning up.

When your agent uses it

  • Stopping whichever autonomous mode is currently running
  • Shutting down a stuck multi-agent Team session
  • Clearing all autonomous mode state after something went wrong

Example prompts

  • “Cancel whatever autonomous mode is currently active.”
  • “Force-clear all OMG mode state, something's stuck.”
  • “Stop the Team session and shut down the teammates.”

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Parse Arguments
  2. Detect Active Modes

What it can do on your machine

Read from SKILL.md and the folder at commit b4f0d9d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

OMG Mode Canceller loads about 690 tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 317 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~690

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from zereight/gitlab-mcp at commit b4f0d9d, republished under its MIT licence (© zereight). 317 words, ~690 tokens.

Download SKILL.mdSave it as .claude/skills/cancel/SKILL.md (or your agent's skills folder).
name
cancel
description
Cancel any active OMG mode and clean up state. Activate when user says: cancel, stop, cancelomg, stopomg, abort, kill it, stop everything.
argument-hint
[--force|--all]

Cancel

Intelligent cancellation that detects and cancels the active OMG mode.

What It Does

Automatically detects which mode is active and cancels it:

  • OMG Autopilot: Stops workflow, preserves progress for resume
  • Ralph: Stops persistence loop
  • Ultrawork: Stops parallel execution
  • UltraQA: Stops QA cycling workflow
  • Team: Sends shutdown to all teammates, cleans up
  • Self-Improve: Stops loop, preserves iteration state for resume

Usage

/cancel
/cancel --force
/cancel --all

Auto-Detection

Reads .omc/state/ to discover which mode is active. Cancels in dependency order:

  1. OMG Autopilot (includes linked ralph/ultraqa cleanup)
  2. Ralph (cleans linked ultrawork)
  3. Ultrawork (standalone)
  4. UltraQA (standalone)
  5. Team (graceful shutdown + cleanup)
  6. Self-Improve (preserve iteration state)

Workflow

1. Parse Arguments

Check for --force or --all flags.

2. Detect Active Modes

Use omg_read_state to check each mode's state file.

3A. Force Mode (--force or --all)

Clear ALL state files in .omc/state/. Nuclear option.

3B. Smart Cancellation (default)
If OMG Autopilot Active
  1. Check for linked ralph → clear ultrawork if linked → clear ralph
  2. Check for linked ultraqa → clear it
  3. Mark omg-autopilot inactive (preserve state for resume)
If Ralph Active (not OMG Autopilot)
  1. Check for linked ultrawork → clear if linked
  2. Clear ralph state
If Team Active
  1. Signal shutdown to all teammates
  2. Wait for responses (15s timeout per member)
  3. Clean up team resources
  4. Clear linked ralph if present
If UltraQA / Ultrawork / Self-Improve Active

Clear state directly.

No Active Modes

Report: "No active OMG modes detected. Use --force to clear all state."

What Gets Preserved

ModeState PreservedResume Command
OMG AutopilotYes (phase, files, spec)/omg-autopilot
Self-ImproveYes (iteration state)/self-improve --resume
RalphNoN/A
OthersNoN/A

Messages

ModeSuccess Message
OMG Autopilot"OMG Autopilot cancelled at phase: {phase}. Progress preserved."
Ralph"Ralph cancelled. Persistent mode deactivated."
Ultrawork"Ultrawork cancelled."
UltraQA"UltraQA cancelled."
Team"Team cancelled. Teammates shut down."
Self-Improve"Self-improve stopped at iteration {N}."
Force"All OMG modes cleared."
None"No active OMG modes detected."

© zereight, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .github/skills/cancel of zereight/gitlab-mcp.

Open the folder on GitHubat commit b4f0d9d

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in zereight/gitlab-mcp, which our catalogue first saw on October 7, 2026.

Compare with similar skills

OMG Mode Canceller next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

OMG Mode Canceller compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
OMG Mode Canceller this skillzereight/gitlab-mcp2k1 repos~690Automated safety check: PassMIT
Zeroshotthe-open-engine/zeroshot1.9k—~2kAutomated safety check: PassMIT
agtx One-Shot Project Runnerfynnfluegge/agtx1.7k—~3.8kAutomated safety check: PassApache-2.0
Self-Improve Evolutionary LoopYeachan-Heo/oh-my-claudecode40k—~5.3kAutomated safety check: WarnMIT
AutopilotYeachan-Heo/oh-my-claudecode40k—~4.4kAutomated safety check: PassMIT
Harness Engineering10xChengTu/harness-engineering1021 repos~1kAutomated safety check: PassNone

Similar skills

  • Zeroshot

    the-open-engine/zeroshot

    Use Zeroshot to prepare, run, observe, or troubleshoot explicit multi-agent software work locally or on Zeroshot Cloud.

    1.9k GitHub stars~2k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Runs a whole project unattended on an agtx kanban board, decomposing the goal, starting tasks, unblocking workers and merging each result.

    1.7k GitHub stars~3.8k tokensUpdated 6 days ago
    Agent WorkflowsAuto-check passed
  • Self-Improve Evolutionary Loop

    Yeachan-Heo/oh-my-claudecode

    Runs an autonomous improvement loop on a repository: agents propose and execute plans, a tournament picks the winner by benchmark, and each round is recorded and plotted.

    40k GitHub stars~5.3k tokensUpdated today
    Agent WorkflowsAuto-check: warnings
  • Autopilot

    Yeachan-Heo/oh-my-claudecode

    Takes a short product idea through requirements, design, planning, parallel implementation, QA cycles and multi-reviewer validation to produce working code.

    40k GitHub stars~4.4k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Harness Engineering

    10xChengTu/harness-engineering

    Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases.

    102 GitHub starsUsed in 1 repo~1k tokens
    Agent WorkflowsAuto-check passed
  • Cursor Orchestrate

    cursor/plugins

    Official

    Splits a large goal into a tree of parallel Cursor cloud agents, with planners, workers and verifiers coordinated by a script and reporting through structured handoffs.

    10k GitHub stars~1.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from zereight/gitlab-mcp

All 24 skills in this repo
  • CCG Tri-Model Orchestration

    zereight/gitlab-mcp

    Runs a task through Codex and Gemini CLIs in parallel alongside Claude, then synthesizes the three outputs into one answer with agreements and conflicts called out.

    2k GitHub starsUsed in 1 repo~657 tokens
    Auto-check passed
  • Shared reference for naming, function size, complexity and error handling rules that reviewer agents apply across TypeScript, Python, Go, Rust, Java, C# and Swift.

    2k GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed
  • Remember Project Knowledge

    zereight/gitlab-mcp

    Sorts what you learned in a session into the right memory surface, filtering out ephemeral notes and duplicates before anything is stored.

    2k GitHub starsUsed in 1 repo~846 tokens
    Auto-check passed
  • Pre-Commit Security Scan

    zereight/gitlab-mcp

    Runs a fast security sweep of recent code changes before a commit or PR, checking for leaked secrets, vulnerable dependencies, unsafe input handling and auth gaps.

    2k GitHub starsUsed in 1 repo~859 tokens
    Auto-check: notes
  • Skill Inventory Stocktake

    zereight/gitlab-mcp

    Audits a project's skill directories for broken frontmatter, missing template sync and quality gaps, then produces a health report of what needs fixing.

    2k GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed
  • OMG Mode Status

    zereight/gitlab-mcp

    Reports which OMG modes are active, such as autopilot, ralph, team, ultraqa and self-improve, with phase, story or cycle progress read from their state files.

    2k GitHub starsUsed in 1 repo~441 tokens
    Auto-check passed

Categories

Questions about OMG Mode Canceller

What does OMG Mode Canceller do?

Detects which autonomous OMG mode is currently active - Autopilot, Ralph, Ultrawork, UltraQA, Team or Self-Improve - and shuts it down cleanly. This skill reads a local state folder to work out which of several autonomous modes is currently running, then cancels it in a dependency-aware order: OMG Autopilot first (including any linked Ralph or UltraQA cleanup), then a standalone Ralph loop, Ultrawork, UltraQA, a running Team, and finally a Self-Improve loop. A force flag skips detection and clears every state file outright.

When should I use OMG Mode Canceller?

OMG Mode Canceller fits situations like: stopping whichever autonomous mode is currently running; shutting down a stuck multi-agent Team session; clearing all autonomous mode state after something went wrong.

How do I install OMG Mode Canceller in Claude Code?

Run `npx skills add zereight/gitlab-mcp --skill cancel -a claude-code`. Or copy the skill folder (.github/skills/cancel in zereight/gitlab-mcp) into .claude/skills/cancel in your project. Claude Code loads it when a task matches its description.

How do I install OMG Mode Canceller in Codex?

Run `npx skills add zereight/gitlab-mcp --skill cancel -a codex`. Or copy the skill folder (.github/skills/cancel in zereight/gitlab-mcp) into .agents/skills/cancel in your project. Codex loads it when a task matches its description.

Can I use OMG Mode Canceller in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zereight/gitlab-mcp --skill cancel -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cancel, .gemini/skills/cancel, .github/skills/cancel and .opencode/skills/cancel in your project.

What does OMG Mode Canceller need to run?

SKILL.md names no scripts, command-line tools or credentials: OMG Mode Canceller is instructions for the agent only.

Does OMG Mode Canceller access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is OMG Mode Canceller safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does OMG Mode Canceller use?

OMG Mode Canceller is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does OMG Mode Canceller use?

About 690 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to OMG Mode Canceller?

Skills that share tags, products or a category with OMG Mode Canceller: Zeroshot (the-open-engine/zeroshot, 1.9k stars), agtx One-Shot Project Runner (fynnfluegge/agtx, 1.7k stars), Self-Improve Evolutionary Loop (Yeachan-Heo/oh-my-claudecode, 40k stars) and Autopilot (Yeachan-Heo/oh-my-claudecode, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains OMG Mode Canceller?

zereight (a GitHub user) maintains it in zereight/gitlab-mcp, which has 2,031 GitHub stars. The repository holds 24 skills in this directory. The repository was last updated on October 9, 2026.

Source: zereight/gitlab-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.