Agent skill

Clawkeeper

by SafeAI-Lab-X in SafeAI-Lab-X/ClawKeeper

Install, configure, verify, and debug the Clawkeeper watcher stack in this workspace.

No licenceAuto-check passedDevOps & Cloud

Install Clawkeeper

skills CLI

$ npx skills add SafeAI-Lab-X/ClawKeeper --skill clawkeeper -a claude-code

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

GitHub CLI

$ gh skill install SafeAI-Lab-X/ClawKeeper clawkeeper --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/SafeAI-Lab-X/ClawKeeper.git skills-src && mkdir -p .claude/skills && cp -r skills-src/legacy/clawkeeper-watcher/skills/clawkeeper .claude/skills/clawkeeper && 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/

Paste into Claude Code

Install the "clawkeeper" agent skill from https://github.com/SafeAI-Lab-X/ClawKeeper/tree/main/legacy/clawkeeper-watcher/skills/clawkeeper into .claude/skills/clawkeeper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clawkeeper", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/SafeAI-Lab-X/ClawKeeper/tree/main/legacy/clawkeeper-watcher/skills/clawkeeper

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add SafeAI-Lab-X/ClawKeeper --skill clawkeeper -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install SafeAI-Lab-X/ClawKeeper clawkeeper --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/SafeAI-Lab-X/ClawKeeper.git skills-src && mkdir -p .agents/skills && cp -r skills-src/legacy/clawkeeper-watcher/skills/clawkeeper .agents/skills/clawkeeper && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "clawkeeper" agent skill from https://github.com/SafeAI-Lab-X/ClawKeeper/tree/main/legacy/clawkeeper-watcher/skills/clawkeeper into .agents/skills/clawkeeper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clawkeeper", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add SafeAI-Lab-X/ClawKeeper --skill clawkeeper -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install SafeAI-Lab-X/ClawKeeper clawkeeper --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/SafeAI-Lab-X/ClawKeeper.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/legacy/clawkeeper-watcher/skills/clawkeeper .cursor/skills/clawkeeper && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "clawkeeper" agent skill from https://github.com/SafeAI-Lab-X/ClawKeeper/tree/main/legacy/clawkeeper-watcher/skills/clawkeeper into .cursor/skills/clawkeeper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clawkeeper", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/SafeAI-Lab-X/ClawKeeper.git --path legacy/clawkeeper-watcher/skills/clawkeeper

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add SafeAI-Lab-X/ClawKeeper --skill clawkeeper -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install SafeAI-Lab-X/ClawKeeper clawkeeper --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/SafeAI-Lab-X/ClawKeeper.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/legacy/clawkeeper-watcher/skills/clawkeeper .gemini/skills/clawkeeper && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "clawkeeper" agent skill from https://github.com/SafeAI-Lab-X/ClawKeeper/tree/main/legacy/clawkeeper-watcher/skills/clawkeeper into .gemini/skills/clawkeeper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clawkeeper", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install SafeAI-Lab-X/ClawKeeper clawkeeper

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add SafeAI-Lab-X/ClawKeeper --skill clawkeeper -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/SafeAI-Lab-X/ClawKeeper.git skills-src && mkdir -p .github/skills && cp -r skills-src/legacy/clawkeeper-watcher/skills/clawkeeper .github/skills/clawkeeper && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "clawkeeper" agent skill from https://github.com/SafeAI-Lab-X/ClawKeeper/tree/main/legacy/clawkeeper-watcher/skills/clawkeeper into .github/skills/clawkeeper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clawkeeper", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add SafeAI-Lab-X/ClawKeeper --skill clawkeeper -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install SafeAI-Lab-X/ClawKeeper clawkeeper --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/SafeAI-Lab-X/ClawKeeper.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/legacy/clawkeeper-watcher/skills/clawkeeper .opencode/skills/clawkeeper && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "clawkeeper" agent skill from https://github.com/SafeAI-Lab-X/ClawKeeper/tree/main/legacy/clawkeeper-watcher/skills/clawkeeper into .opencode/skills/clawkeeper/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "clawkeeper", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: clawkeeper
GitHub stars: 1k
Token cost: ~1.8k tokens
SKILL.md length: 653 words
Files: 1
Skills in repo: 11
Repo updated: Aug 17, 2026
First seen: Oct 7, 2026
Licence: None found

At a glance

Install, configure, verify, and debug the Clawkeeper watcher stack in this workspace.

Works in 5 steps: Identify whether the user wants install,… → Check whether the issue is about the… → Verify the exact mode in play: remote,… → …
A user asks to set up clawkeeper
SKILL.md covers Core mental model, Preferred workflow, Install and initialize and Validation commands, plus 4 more sections
Calls npm and pnpm

What it does

Clawkeeper is an agent skill from SafeAI-Lab-X/ClawKeeper. Install, configure, verify, and debug the Clawkeeper watcher stack in this workspace. Use when a user asks to set up clawkeeper, initialize remote or local mode, enable clawkeeper-watcher, wire clawkeeper-bands, diagnose context-judge routing, inspect watcher logs, fix mode/config mismatches, or troubleshoot startup, audit, hardening, rollback, drift monitoring, or bridge notification issues.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud. The repository describes itself as: ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers (aka The Norton for OpenClaw).

When your agent uses it

A user asks to set up clawkeeper
Initialize remote
Enable clawkeeper-watcher
Wire clawkeeper-bands

Example prompts

“/clawkeeper”

Requirements

Node.js

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

Identify whether the user wants install, config, validation, or debugging.
Check whether the issue is about the launcher, the watcher plugin, or the bands bridge.
Verify the exact mode in play: remote, local, or both.
Run the smallest direct validation command first.
Only after validation fails, inspect config, logs, bridge wiring, and code paths.

What it can do on your machine

Read from SKILL.md and the folder at commit 69db077. 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
Shell commands in SKILL.md call:
- npm
- pnpm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm and pnpm, which can reach the network depending on how they are called.
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

Clawkeeper loads about 1.8k tokens when it runs. Until then it costs about 105 tokens; SKILL.md has 653 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~105
When it runs · the whole SKILL.md, loaded when a task matches: ~1.8k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 653 words (~1,776 tokens).

“Use this skill only for the Clawkeeper workspace. Treat clawkeeper-watcher as the product center and clawkeeper as the launcher that prepares mode-specific runtime state.”

— opening of SKILL.md by SafeAI-Lab-X

name: clawkeeper

Outline of SKILL.md

Clawkeeper
Core mental model
Preferred workflow
Install and initialize
Validation commands
Launcher validation
Mode launch validation
Watcher validation
Context-judge validation
Bridge validation
Debugging order
Common failure patterns
Local command run in remote mode
gateway.mode mismatch
Wrong route when testing context judgment
Bridge configured but notifications do not arrive
Logs exist but the wrong file is inspected
Audit result interpreted as host hardening
Command accuracy guardrails
Response expectations

Read the full SKILL.md on GitHub

Files

Just SKILL.md in legacy/clawkeeper-watcher/skills/clawkeeper of SafeAI-Lab-X/ClawKeeper.

Open the folder on GitHubat commit 69db077

Compare with similar skills

Clawkeeper 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.

Clawkeeper compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Clawkeeper this skillSafeAI-Lab-X/ClawKeeper	1k	—	~1.8k	Automated safety check: Pass	None	1 mo ago
Monitor CInrwl/nx	29k	6 repos	~4.7k	Automated safety check: Pass	MIT	today
Repo Hygiene Scan and FixQwenLM/qwen-code	28k	—	~1.7k	Automated safety check: Pass	Apache-2.0	today
Bash Defensive Patternspromovaweb/setupvibe	102	14 repos	~572	Automated safety check: Pass	GPL-3.0	1 mo ago
Terravision Cloud Diagramspatrickchugh/terravision	1.6k	—	~5.6k	Automated safety check: Notes	AGPL-3.0-only	2 days ago
Author Migrationnrwl/nx	29k	—	~12k	Automated safety check: Notes	MIT	today

Similar skills

Monitor CI
nrwl/nx
Monitor Nx Cloud CI pipeline and handle self-healing fixes. An agent skill from nrwl/nx.
29k GitHub starsUsed in 6 repos~4.7k tokens
DevOps & CloudAuto-check passed
Repo Hygiene Scan and Fix
QwenLM/qwen-code
Scheduled CI skill that scans a repository for small, certain docs, test and code hygiene issues and fixes them on one branch with a commit per finding.
28k GitHub stars~1.7k tokensUpdated today
DevOps & CloudAuto-check passed
Bash Defensive Patterns
promovaweb/setupvibe
Master defensive Bash programming techniques for production-grade scripts.
102 GitHub starsUsed in 14 repos~572 tokens
DevOps & CloudAuto-check passed
Terravision Cloud Diagrams
patrickchugh/terravision
Draw cloud architecture diagrams for AWS, Azure or GCP with the official provider icon sets, using TerraVision.
1.6k GitHub stars~5.6k tokensUpdated 2 days ago
DevOps & CloudAuto-check: notes
Author Migration
nrwl/nx
Author or scope a first-party Nx migration. An agent skill from nrwl/nx.
29k GitHub stars~12k tokensUpdated today
DevOps & CloudAuto-check: notes
NGINX Ingress Controller Feature Checklists
nginx/kubernetes-ingress
Gives step-by-step checklists for adding Ingress annotations, VirtualServer fields and Helm values to the NGINX Kubernetes Ingress Controller, with common gotchas.
5.1k GitHub stars~1.4k tokensUpdated today
DevOps & CloudAuto-check passed

Questions about Clawkeeper

What does Clawkeeper do?

Install, configure, verify, and debug the Clawkeeper watcher stack in this workspace. Clawkeeper is an agent skill from SafeAI-Lab-X/ClawKeeper. Install, configure, verify, and debug the Clawkeeper watcher stack in this workspace.

When should I use Clawkeeper?

Clawkeeper fits situations like: A user asks to set up clawkeeper; initialize remote; enable clawkeeper-watcher; wire clawkeeper-bands.

How do I install Clawkeeper in Claude Code?

Run `npx skills add SafeAI-Lab-X/ClawKeeper --skill clawkeeper -a claude-code`. Or copy the skill folder (legacy/clawkeeper-watcher/skills/clawkeeper in SafeAI-Lab-X/ClawKeeper) into .claude/skills/clawkeeper in your project. Claude Code loads it when a task matches its description.

How do I install Clawkeeper in Codex?

Run `npx skills add SafeAI-Lab-X/ClawKeeper --skill clawkeeper -a codex`. Or copy the skill folder (legacy/clawkeeper-watcher/skills/clawkeeper in SafeAI-Lab-X/ClawKeeper) into .agents/skills/clawkeeper in your project. Codex loads it when a task matches its description.

Can I use Clawkeeper 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 SafeAI-Lab-X/ClawKeeper --skill clawkeeper -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/clawkeeper, .gemini/skills/clawkeeper, .github/skills/clawkeeper and .opencode/skills/clawkeeper in your project.

What does Clawkeeper need to run?

Going by SKILL.md and its folder, Clawkeeper needs the command-line tools its instructions call (npm and pnpm). Our summary lists: Node.js.

Does Clawkeeper access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Clawkeeper 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 Clawkeeper use?

No licence was found for Clawkeeper or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Clawkeeper use?

About 1.8k tokens (SKILL.md is roughly 7.1k 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 Clawkeeper?

Skills that share tags, products or a category with Clawkeeper: Monitor CI (nrwl/nx, 29k stars), Repo Hygiene Scan and Fix (QwenLM/qwen-code, 28k stars), Bash Defensive Patterns (promovaweb/setupvibe, 102 stars) and Terravision Cloud Diagrams (patrickchugh/terravision, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Clawkeeper?

SafeAI-Lab-X (a GitHub user) maintains it in SafeAI-Lab-X/ClawKeeper, which has 1,024 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on August 17, 2026.

Source: SafeAI-Lab-X/ClawKeeper on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Clawkeeper

Install Clawkeeper

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Files

Compare with similar skills

Similar skills

Monitor CI

Repo Hygiene Scan and Fix

Bash Defensive Patterns

Terravision Cloud Diagrams

Author Migration

NGINX Ingress Controller Feature Checklists

More from SafeAI-Lab-X/ClawKeeper

Feishu Safety Guide

Node Connect

Openclaw Ghsa Maintainer

Openclaw PR Maintainer

Openclaw Release Maintainer

Openclaw Test Heap Leaks

Questions about Clawkeeper

Install Clawkeeper

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Files

Compare with similar skills

Similar skills

More from SafeAI-Lab-X/ClawKeeper

Related

Questions about Clawkeeper