ClawSweeper is a maintenance bot for OpenClaw repositories that periodically reviews open issues and pull requests and identifies candidates for closure, repair, or guarded automerging. It is intended for repository maintainers running their own configured instance. The catalogue entries are skills and an instruction for its review and maintenance workflows.
Borrowing it
Nothing to install: this file belongs to openclaw/clawsweeper. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/openclaw/clawsweeper/main/.agents/skills/local-clawsweeper-review/SKILL.mdgit clone --depth 1 https://github.com/openclaw/clawsweeperWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/openclaw/clawsweeper/local-clawsweeper-review)<a href="https://agentmods.dev/skills/openclaw/clawsweeper/local-clawsweeper-review"><img src="https://agentmods.dev/badge/skills/openclaw/clawsweeper/local-clawsweeper-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/openclaw/clawsweeper/local-clawsweeper-review"><img src="https://agentmods.dev/badge/skills/openclaw/clawsweeper/local-clawsweeper-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.01555 |
| Opus 5.5 | $0.00010 | $0.00622 |
| Sonnet 5.5 | $0.00005 | $0.00311 |
| Haiku 4.5 | $0.00002 | $0.00155 |
Grade A, and why
local-clawsweeper-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local ClawSweeper Review
Use this skill when someone wants read-only local ClawSweeper output before submitting, updating, or re-reviewing an issue or PR.
Safety Boundary
- Run only
pnpm run review -- --local-onlyfor an existing GitHub item, orpnpm run review -- --local-rangefor a pre-submission committed range. - Do not run
apply-artifacts,apply-decisions, GitHub comment posting, or merge/autofix commands unless the user explicitly asks for that mutation. - Do not print
OPENAI_API_KEY,CODEX_API_KEY,CODEX_ACCESS_TOKEN, GitHub tokens, or Codex auth material. - Treat generated review artifacts as local proof. Do not claim ClawSweeper posted or synced anything unless a separate explicit mutation command did it.
Locate ClawSweeper
Prefer the current repository when its package.json name is
@openclaw/clawsweeper. Otherwise use a known clean local checkout:
- Windows:
C:\oc-work\clawsweeper-source - POSIX fallback:
~/Projects/clawsweeper
Inspect git status --short before making changes. If another ClawSweeper clone
is dirty or ambiguous, do not use it for the local review runner.
First-Time Setup
From the ClawSweeper checkout:
corepack enable
pnpm install
pnpm run build:all
pnpm run codex:local:check -- --diagnostics
The diagnostics mode checks the selected Codex binary and login status without
a model request. It does not prove model access or review readiness. Omit
--diagnostics for the existing model smoke test, which consumes model usage.
If the Codex check says the CLI is not logged in, have the operator authenticate their own Codex CLI. Device auth is the simplest shareable setup:
codex login --device-auth -c 'service_tier="fast"'
For API-key setup, pass the key through the shell only for the login command and then clear it from the environment. Do not put the key in docs, scripts, shell history, or committed files.
PowerShell:
$env:OPENAI_API_KEY = Read-Host "OpenAI API key"
$env:OPENAI_API_KEY | codex login --with-api-key -c 'service_tier="fast"'
Remove-Item Env:OPENAI_API_KEY
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 14d ago Changed · +10 lines 49e0448181eb
- 2mo ago First seen · 177 lines · 24 tokens per session scan A 5590e3fe3f59
local-clawsweeper-review is a skill published in the GitHub repository openclaw/clawsweeper (2,004 stars, last pushed today), licensed MIT. It adds 24 tokens to every session and 1,555 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
apex-review
Cross-cutting review of recent work — catches gaps between specialists. Use when asked to "review what we built", "check the work", "pre-launch review", or after completing a significant chunk of work.
code-reviewer
A code-reviewing role that checks code for bugs, security weaknesses, readability problems, design issues, and performance concerns.
prism
Prism's local index of this repository. Use before editing, renaming or deleting unfamiliar code, to orient in a new repo, to review a PR or diff, to pick a lens, or to run a saved habit.
code-review
A code-review and quality-analysis skill written in Chinese. It is intended to inspect code, find potential problems, and suggest improvements.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
openclaw-pr-maintainer
Maintainer workflow for reviewing, triaging, preparing, closing, or landing OpenClaw pull requests and related issues. Use when Codex needs to validate bug-fix claims, search for related issues or PRs, apply or recommend close/reason labels, prepare GitHub comments safely, check review-thread follow-up, or perform…