Agent skill · Security

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.

SafeAI-Lab-Xgithub.com/SafeAI-Lab-XGitHub ↗
claude-code
Install
npx skills add SafeAI-Lab-X/ClawKeeper --skill clawkeeper --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 7 KB
Bundled scripts: none
Path: legacy/clawkeeper-watcher/skills/clawkeeper/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 1,034
Language: TypeScript

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Clawkeeper 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. ## Core mental model - `plugins/clawkeeper-watcher/` is the watcher plugin and governance engine. - `clawkeeper/` is the launcher that prepares isolated `remote` and `local` mode roots, then delegates to OpenClaw. - `plugins/clawkeeper-bands/` is the user-side bridge for notifications and approvals. - `remote` is read-only judgment and historical intelligence. - `local` is trusted audit, hardening, rollback, drift monitoring, and skill guard. - Both watcher modes expose `POST /plugins/clawkeeper-watcher/context-judge`. Read these files when needed: - `README.md` - `plugins/clawkeeper-watcher/README.md` - `plugins/clawkeeper-bands/README.md` - `clawkeeper/src/cli.ts` ## Preferred workflow Follow this order unless the user explicitly narrows the task: 1. Identify whether the user wants install, config, validation, or debugging. 2. Check whether the issue is about the launcher, the watcher plugin, or the bands bridge. 3. Verify the exact mode in play: `remote`, `local`, or both. 4. Run the smallest d

What's inside
Steps it walks through
  1. Core mental model
  2. Preferred workflow
  3. Install and initialize
  4. Validation commands
  5. Launcher validation
  6. Mode launch validation
  7. Watcher validation
  8. Context-judge validation
  9. Bridge validation
  10. Debugging order
  11. Common failure patterns
  12. Local command run in remote mode
  13. gateway.mode mismatch
  14. Wrong route when testing context judgment
Commands it runs
pnpm install
cd clawkeeper
npm install
npm run build
npm link
cd ..
clawkeeper init remote
clawkeeper init local
clawkeeper local config set gateway.mode local
clawkeeper status
More from ClawKeeper
All skills →
About this skill
What does the clawkeeper skill do?

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.

How do I install it?

Run `npx skills add SafeAI-Lab-X/ClawKeeper --skill clawkeeper --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From SafeAI-Lab-X/ClawKeeper, a repository with 1,034 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going