runaway-stopper

garrytan/gstack Agent tooling

runaway-stopper is a skill in garrytan/gstack, last changed 3 Nov 2026. It can run shell commands and pre-approve tools — read the findings before installing.

From the author

Find runaway Capy threads and subagents, stop or rotate them safely, and prevent repeats. (gstack)

How much a skill can do, not whether it is risky.

Pattern check

1 item to review

Broad tools pre-approved in allowed-tools

R34 · High · SKILL.md:12

Commit 673a336 · 6 Nov 2026

How the check works

Pattern check:1 item to reviewSee it

QAI Index

69/QI

We rate every listed skill the same way, from 0 to 100.

A guide to compare by, not a verdict on the skill.

How it's scored

Install

Each tab says whether it installs commit 673a336, the one we checked, or the latest version.

OpenCode also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Goose also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Windsurf (Devin Desktop) also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Zed also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Roo Code also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Factory Droid also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Junie also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Amp also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

No install command here reaches Kiro. Copy the skill's folder into .kiro/skills/ in your project, or ~/.kiro/skills/ for all your projects. garrytan/gstack/runaway-stopper (opens in a new tab)

Antigravity also looks in .agents/skills/, so the Any agent steps reach it with This project. For All projects, see where Antigravity looks.

Cline also looks in .claude/skills/, so the Claude Code steps reach it with This project. For All projects, see where Cline looks.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie and Amp. With This project, Any agent also reaches Antigravity and Claude Code reaches Cline. Kiro needs the folder copied by hand.

Read this before installing: Broad tools pre-approved in allowed-tools — SKILL.md:12

Pinned to commit 673a336, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/garrytan/gstack.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 673a336bc447061c445a53ff44f50486556053a0 &&git -C "$tmp" sparse-checkout set -- runaway-stopper &&git -C "$tmp" checkout -q 673a336bc447061c445a53ff44f50486556053a0 &&mkdir -p .claude/skills &&mkdir .claude/skills/runaway-stopper &&cp -R "$tmp"/runaway-stopper/. .claude/skills/runaway-stopper/ &&rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Claude Code docs

Pinned to commit 673a336, the one we checked.

Skills in the Claude apps belong to your account rather than to a project.

Make runaway-stopper.zip, with the skill folder at the top level:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/garrytan/gstack.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 673a336bc447061c445a53ff44f50486556053a0 &&git -C "$tmp" sparse-checkout set -- runaway-stopper &&git -C "$tmp" checkout -q 673a336bc447061c445a53ff44f50486556053a0 &&out="$(mktemp -d)" &&cp -R "$tmp"/runaway-stopper "$out"/runaway-stopper &&(cd "$out" && zip -qr - runaway-stopper) > runaway-stopper.zip &&rm -rf "$tmp" "$out"

In Claude, open Customize > Skills, select +, then + Create skill > Upload a skill, and choose runaway-stopper.zip.

On Free, Pro and Max plans, turn on Code execution and file creation (Create and edit files in newer settings) under Settings > Capabilities.

Claude apps docs

Pinned to commit 673a336, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/garrytan/gstack.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 673a336bc447061c445a53ff44f50486556053a0 &&git -C "$tmp" sparse-checkout set -- runaway-stopper &&git -C "$tmp" checkout -q 673a336bc447061c445a53ff44f50486556053a0 &&mkdir -p .agents/skills &&mkdir .agents/skills/runaway-stopper &&cp -R "$tmp"/runaway-stopper/. .agents/skills/runaway-stopper/ &&rm -rf "$tmp"

Codex picks up new skills on its own; restart it if this one does not appear.

Codex docs

Pinned to commit 673a336, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/garrytan/gstack.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 673a336bc447061c445a53ff44f50486556053a0 &&git -C "$tmp" sparse-checkout set -- runaway-stopper &&git -C "$tmp" checkout -q 673a336bc447061c445a53ff44f50486556053a0 &&mkdir -p .cursor/skills &&mkdir .cursor/skills/runaway-stopper &&cp -R "$tmp"/runaway-stopper/. .cursor/skills/runaway-stopper/ &&rm -rf "$tmp"

Cursor docs

Pinned to commit 673a336, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/garrytan/gstack.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 673a336bc447061c445a53ff44f50486556053a0 &&git -C "$tmp" sparse-checkout set -- runaway-stopper &&git -C "$tmp" checkout -q 673a336bc447061c445a53ff44f50486556053a0 &&mkdir -p .github/skills &&mkdir .github/skills/runaway-stopper &&cp -R "$tmp"/runaway-stopper/. .github/skills/runaway-stopper/ &&rm -rf "$tmp"

In a running Copilot CLI session, run /skills reload.

Or install it with gh skill, which also installs the commit we checked. Needs GitHub CLI 2.90 or later.

gh skill install garrytan/gstack runaway-stopper/SKILL.md@673a336bc447061c445a53ff44f50486556053a0 --agent github-copilot --scope project

Copilot & VS Code docs

Pinned to commit 673a336, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/garrytan/gstack.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 673a336bc447061c445a53ff44f50486556053a0 &&git -C "$tmp" sparse-checkout set -- runaway-stopper &&git -C "$tmp" checkout -q 673a336bc447061c445a53ff44f50486556053a0 &&mkdir -p .gemini/skills &&mkdir .gemini/skills/runaway-stopper &&cp -R "$tmp"/runaway-stopper/. .gemini/skills/runaway-stopper/ &&rm -rf "$tmp"

In a running session, run /skills reload.

Or use Gemini CLI’s own installer. Installs the latest version, not the one we checked.

gemini skills install https://github.com/garrytan/gstack.git --path runaway-stopper --scope workspace

Gemini CLI docs

Pinned to commit 673a336, the one we checked.

OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity read .agents/skills in a project.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/garrytan/gstack.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 673a336bc447061c445a53ff44f50486556053a0 &&git -C "$tmp" sparse-checkout set -- runaway-stopper &&git -C "$tmp" checkout -q 673a336bc447061c445a53ff44f50486556053a0 &&mkdir -p .agents/skills &&mkdir .agents/skills/runaway-stopper &&cp -R "$tmp"/runaway-stopper/. .agents/skills/runaway-stopper/ &&rm -rf "$tmp"

Or use the skills CLI from skills.sh. Installs the latest version, not the one we checked. The skills CLI reports installs to skills.sh unless you set DISABLE_TELEMETRY=1.

npx skills@1.7.4 add garrytan/gstack --skill runaway-stopper

Agent Skills docs

Read SKILL.md first

MIT

Licence

140.3k

Repo stars

Folder last changed

Publisher

Files

Checked

6 Nov 2026

What it can touch

From the files and frontmatter at commit 673a336. This is how much a skill can do, not whether it is risky.

Runs shell commands
Its instructions or files give the agent commands to run on your computer.
Pre-approves tools
Its allowed-tools field lists tools the agent may use without asking you first, in agents that honour it.
SKILL.md:12 (opens in a new tab)

Pattern check

Pattern check: 1 item to review · commit 673a336 · 6 Nov 2026

R34 · HighBroad tools pre-approved in allowed-tools
SKILL.md:12 (opens in a new tab)
```
- Bash
```

We checked every text file in this skill, at commit 673a336 on 6 Nov 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check works Report an incorrect finding

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

Agent Skills specPasses with warnings
The open format from agentskills.io, held to the strictest version of each rule among the agents we check.
- Warning
  Fields outside the spec: preamble-tier, version and triggers. Uploads to the Claude apps and API, and the spec's validator, reject the file; most agents ignore these fields. O1
  Fix: Delete them for a portable skill, or keep them if you only target the agents that read them.
- Warning
  allowed-tools is a list; the spec defines a space-separated string. gh skill publish rejects a list, though Claude Code accepts one. O5
  Fix: Write it on one line: allowed-tools: Bash Read Write
- Note
  The description doesn't say when to use the skill. D6
  Fix: Add a sentence such as "Use when …" naming the requests or files that should trigger it.
- Note
  There is no license field, so readers can't tell whether they may reuse the skill. O2
  Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.
Claude CodePasses
Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.
- Note
  Claude Code ignores fields it doesn't know: preamble-tier, version and triggers. O1
  Fix: Check the spelling against Claude Code's field list, or delete them.
Claude apps & API uploadFails
Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.
- Error
  Upload and packaging fail on fields outside the spec: preamble-tier, version and triggers. O1
  Fix: Delete them, and keep your own data under metadata as text values.
- Note
  allowed-tools is a list; the spec defines a space-separated string. O5
  Fix: Write it on one line: allowed-tools: Bash Read Write
OpenAI (Codex & API)Passes with warnings
Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.
- Warning
  Fields outside the spec: preamble-tier, version and triggers. Codex ignores them; OpenAI doesn't say whether its upload accepts them. O1
  Fix: Delete them, or move your own data under metadata as text values.
- Note
  allowed-tools is a list; the spec defines a space-separated string. O5
  Fix: Write it on one line: allowed-tools: Bash Read Write
VS Code & CopilotPasses
VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.
- Note
  VS Code ignores fields it doesn't support: preamble-tier, version and triggers. O1
  Fix: Delete them unless another agent you target reads them.
- Note
  allowed-tools is a list; the spec defines a space-separated string. O5
  Fix: Write it on one line: allowed-tools: Bash Read Write

SKILL.md

Read SKILL.md on GitHub

Files

4 files

Path	Size
SKILL.md (opens in a new tab)	15.1 KB
SKILL.md.tmpl (opens in a new tab)	7.3 KB
templates/rotation-handoff.md (opens in a new tab)	1.2 KB
templates/successor-brief.md (opens in a new tab)	1 KB

More from garrytan/gstack

Skill	QAI Index	What it can touch	Pattern check	Licence	Updated
autoplanAuto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. (gstack) 69/QI Adds hooks +6 more Pattern check: 1 item to reviewMITUpdated 3 Nov 2026	69/QI	Adds hooks Touches credentials +5 more	Pattern check: 1 item to review	MIT	3 Nov 2026
benchmarkWeb performance regression detection. (gstack) 64/QI Runs shell commands +2 more Pattern check: 1 item to reviewMITUpdated 28 Oct 2026	64/QI	Runs shell commands Names web addresses +1 more	Pattern check: 1 item to review	MIT	28 Oct 2026
benchmark-modelsCross-model benchmark for gstack skills. (gstack) 64/QI Touches credentials +2 more Pattern check: 1 item to reviewMITUpdated 30 Oct 2026	64/QI	Touches credentials Runs shell commands +1 more	Pattern check: 1 item to review	MIT	30 Oct 2026
canaryPost-deploy canary monitoring. (gstack) 64/QI Runs shell commands +2 more Pattern check: 1 item to reviewMITUpdated 2 Nov 2026	64/QI	Runs shell commands Reaches the network +1 more	Pattern check: 1 item to review	MIT	2 Nov 2026
captainRun a crew of coding agents from one controller (also /crew): lanes send READY blocks and never merge; the controller merges through trains, keeps the digest, relays approvals, fixes flakes daily. (gstack) 69/QI Runs shell commands +1 more Pattern check: 1 item to reviewMITUpdated 5 Nov 2026	69/QI	Runs shell commands Pre-approves tools	Pattern check: 1 item to review	MIT	5 Nov 2026
codexOpenAI Codex CLI wrapper — three modes. (gstack) 64/QI Downloads software +4 more Pattern check: 1 item to reviewMITUpdated 2 Nov 2026	64/QI	Downloads software Runs shell commands +3 more	Pattern check: 1 item to review	MIT	2 Nov 2026

All skills in garrytan/gstack

Other Agent tooling skills

Same category, most repo stars first.

Skill	QAI Index	What it can touch	Pattern check	Licence	Updated
brainstormingYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). obra/superpowers 80/QI Runs shell commands +3 more Pattern check: Nothing flaggedMITUpdated 3 Nov 2026	80/QI	Runs shell commands Reaches the network +2 more	Pattern check: Nothing flagged	MIT	3 Nov 2026
executing-plansUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available obra/superpowers 75/QI Runs shell commands +1 more Pattern check: Nothing flaggedMITUpdated 3 Nov 2026	75/QI	Runs shell commands Bundles scripts	Pattern check: Nothing flagged	MIT	3 Nov 2026
agent-architecture-auditFull-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack. affaan-m/ECC 69/QI Runs shell commands Pattern check: Nothing flaggedMITUpdated 11 Aug 2026	69/QI	Runs shell commands	Pattern check: Nothing flagged	MIT	11 Aug 2026
agent-sortBuild an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle. affaan-m/ECC 71/QI Runs shell commands Pattern check: Nothing flaggedMITUpdated 11 Jun 2026	71/QI	Runs shell commands	Pattern check: Nothing flagged	MIT	11 Jun 2026
claude-apiReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-`, `us.anthropic.`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai\|langchain_openai\|google.generativeai\|genai\|mistralai\|cohere\|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). anthropics/skills 73/QI Touches credentials +6 more Pattern check: 1 item to reviewApache 2.0Updated 9 Oct 2026	73/QI	Touches credentials Downloads software +5 more	Pattern check: 1 item to review	Apache 2.0	9 Oct 2026
mcp-builderGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). anthropics/skills 89/QI Touches credentials +4 more Pattern check: Nothing flaggedApache 2.0Updated 28 Oct 2026	89/QI	Touches credentials Runs shell commands +3 more	Pattern check: Nothing flagged	Apache 2.0	28 Oct 2026

At a glance

What it can touch

Pattern check

QAI Index

Install

Claude Code

Claude apps

Codex

Cursor

Copilot & VS Code

Gemini CLI

Any agent

What it can touch

Pattern check

Format check

SKILL.md

Files

More from garrytan/gstack

Other Agent tooling skills