Agent skill

Local Clawsweeper Review

by openclaw in openclaw/clawsweeper

Run local ClawSweeper exact-item or committed-range reviews without GitHub mutation.

MITAuto-check passed

Install Local Clawsweeper Review

skills CLI
$ npx skills add openclaw/clawsweeper --skill local-clawsweeper-review -a claude-code

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

GitHub CLI
$ gh skill install openclaw/clawsweeper local-clawsweeper-review --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/openclaw/clawsweeper.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/local-clawsweeper-review .claude/skills/local-clawsweeper-review && 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
local-clawsweeper-review
GitHub stars
2k
Token cost
~1.4k tokens
SKILL.md length
657 words
Files
2
Skills in repo
2
Repo updated
First seen
Licence
MIT

At a glance

Run local ClawSweeper exact-item or committed-range reviews without GitHub mutation.

  • SKILL.md covers Safety Boundary, Locate ClawSweeper, First-Time Setup and Target Checkout Modes, plus 3 more sections
  • Calls pnpm, git and codex; needs OPENAI_API_KEY and CODEX_API_KEY

What it does

Local Clawsweeper Review is an agent skill from openclaw/clawsweeper. Run local ClawSweeper exact-item or committed-range reviews without GitHub mutation.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It works with GitHub. The repository describes itself as: ClawSweeper scans all issues and PRs and suggest what we can close, and why. It runs every PR / Issue once a week. The licence is MIT.

Example prompts

  • “/local-clawsweeper-review”

Requirements

  • A credential in OPENAI_API_KEY
  • A credential in CODEX_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit acf20cf. 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:

    • pnpm
    • git
    • codex
    • gh

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

  • Network

    No URLs in SKILL.md. Its commands use pnpm, git and gh, 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 these keys or tokens, usually read from environment variables:

    • OPENAI_API_KEY
    • CODEX_API_KEY
    • CODEX_ACCESS_TOKEN

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

Context cost

Local Clawsweeper Review loads about 1.4k tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 657 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~27
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 openclaw/clawsweeper at commit acf20cf, republished under its MIT licence (© openclaw). 657 words, ~1,415 tokens.

Download SKILL.mdSave it as .claude/skills/local-clawsweeper-review/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
local-clawsweeper-review
description
Run local ClawSweeper exact-item or committed-range reviews without GitHub mutation.

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-only for an existing GitHub item, or pnpm run review -- --local-range for 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:

sh
corepack enable
pnpm install
pnpm run build:all
pnpm run codex:local:check

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:

sh
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:

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

POSIX shell:

sh
printf '%s' "$OPENAI_API_KEY" | codex login --with-api-key -c 'service_tier="fast"'
unset OPENAI_API_KEY

If the wrong Codex binary is used, set CODEX_BIN in the local shell for that run. Otherwise, --local-only uses the first spawnable codex command on PATH, including on Windows. If no Windows PATH command is spawnable, it falls back to the installed Codex Desktop binary.

Target Checkout Modes

By default, an exact local PR review manages its own target checkout under artifacts/local-review-<pr-number>/target.

By default, --local-range reviews the clean checkout where the command was invoked. It does not manage or switch that checkout. Pass --target-dir when the branch to review is elsewhere.

Pass --target-dir when the operator wants to review an existing checkout or an issue.

Use a clean target checkout of the repository being reviewed. Prefer a dedicated review checkout if the normal worktree is dirty:

  • Windows: C:\oc-work\clawsweeper-local-target-openclaw
  • POSIX fallback: ../openclaw

Before reviewing against main, update the target checkout only when it is clean:

sh
git -C <target-dir> status --short
git -C <target-dir> fetch origin main
git -C <target-dir> switch main
git -C <target-dir> pull --ff-only origin main

Do not switch branches, pull, or overwrite files in a dirty target checkout.

Show full SKILL.md (284 more words)Show less

Run A Local Review

Use the exact issue or PR number. If the number is not provided and the current branch has an open PR, use gh pr view --json number,url,headRefOid to identify it.

From the ClawSweeper checkout:

sh
pnpm run review -- --local-only --item-number <pr-number>

To use a supplied checkout or review an issue:

sh
pnpm run review -- --local-only \
  --item-number <issue-or-pr-number> \
  --target-dir <target-dir>

To review committed branch work before a PR exists:

sh
pnpm run review -- --local-range \
  --target-repo <owner/repo> \
  --base origin/main

The range is merge-base(<base>, HEAD)..HEAD. It must be clean and contain at least one commit beyond the base. This path withholds GitHub credentials, isolates cached gh auth, disables web search, and skips host-side URL/media preprocessing. It still calls the configured Codex model service; do not call it air-gapped or fully network-offline.

The exact local command prints a human-readable progress summary by default. Add --verbose only when debugging checkout, selection, or Codex process details.

For quick smoke tests, lower --batch-size, --shard-count, --max-pages, and --codex-timeout-ms, but label the result as a smoke run rather than a full local review.

Read The Artifact

The default OpenClaw report is written to:

text
<artifact-dir>/<issue-or-pr-number>.md

Read the artifact and summarize:

  • review_status
  • main_sha
  • pull_head_sha for PRs
  • decision/confidence/action fields when present
  • findings or blockers
  • exact Codex/auth/runtime failure if the run failed

If the failure is Codex auth, stop after providing the local setup command. If the failure is runner/runtime behavior, include the artifact path and a concise stderr or log summary.

Closeout

Before reporting success:

  • Confirm the command used review --local-only or review --local-range.
  • Confirm no GitHub comments, labels, merges, or apply commands were run.
  • Confirm the target checkout is still clean.
  • If findings exist, list the actionable items and the next local fix/test step.
  • If no blockers exist, say the local ClawSweeper artifact found no blockers and include the reviewed main_sha and PR head SHA when available.

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

Files

SKILL.md and 1 other file in .agents/skills/local-clawsweeper-review of openclaw/clawsweeper.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit acf20cf

Compare with similar skills

Local Clawsweeper Review 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.

Local Clawsweeper Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Local Clawsweeper Review this skillopenclaw/clawsweeper2k—~1.4kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Greplooponyx-dot-app/onyx32k4 repos~3.3kAutomated safety check: PassMIT
GitHub Deep Researchbytedance/deer-flow84k4 repos~1.3kAutomated safety check: PassMIT
Diagnosing Superpowers Sessionsobra/superpowers297k3 repos~1.7kAutomated safety check: PassMIT
Update V8 Versionopeninterpreter/openinterpreter69k2 repos~845Automated safety check: PassApache-2.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed
  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    84k GitHub starsUsed in 4 repos~1.3k tokens
    Research & ScienceAuto-check passed
  • Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.

    297k GitHub starsUsed in 3 repos~1.7k tokens
    Agent WorkflowsAuto-check passed
  • Update V8 Version

    openinterpreter/openinterpreter

    Bumps the pinned v8 and rusty_v8 versions in Codex, validates the release-candidate path with the v8-canary check, and traces failures to upstream build changes.

    69k GitHub starsUsed in 2 repos~845 tokens
    DevOps & CloudAuto-check passed
  • Last30days

    mvanhorn/last30days-skill

    Research what people actually say about any topic in the last 30 days.

    64k GitHub stars~7.9k tokensUpdated today
    Research & ScienceAuto-check: notes

More from openclaw/clawsweeper

  • Crabbox

    openclaw/clawsweeper

    Use the Crabbox wrapper for validation across Linux, macOS, Windows, and WSL2, including delegated Blacksmith Testbox proof.

    2k GitHub stars~9.9k tokensUpdated today
    Auto-check: notes

Works with

Questions about Local Clawsweeper Review

What does Local Clawsweeper Review do?

Run local ClawSweeper exact-item or committed-range reviews without GitHub mutation. Local Clawsweeper Review is an agent skill from openclaw/clawsweeper. Run local ClawSweeper exact-item or committed-range reviews without GitHub mutation.

How do I install Local Clawsweeper Review in Claude Code?

Run `npx skills add openclaw/clawsweeper --skill local-clawsweeper-review -a claude-code`. Or copy the skill folder (.agents/skills/local-clawsweeper-review in openclaw/clawsweeper) into .claude/skills/local-clawsweeper-review in your project. Claude Code loads it when a task matches its description.

How do I install Local Clawsweeper Review in Codex?

Run `npx skills add openclaw/clawsweeper --skill local-clawsweeper-review -a codex`. Or copy the skill folder (.agents/skills/local-clawsweeper-review in openclaw/clawsweeper) into .agents/skills/local-clawsweeper-review in your project. Codex loads it when a task matches its description.

Can I use Local Clawsweeper Review 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 openclaw/clawsweeper --skill local-clawsweeper-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/local-clawsweeper-review, .gemini/skills/local-clawsweeper-review, .github/skills/local-clawsweeper-review and .opencode/skills/local-clawsweeper-review in your project.

What does Local Clawsweeper Review need to run?

Going by SKILL.md and its folder, Local Clawsweeper Review needs the command-line tools its instructions call (pnpm, git, codex and gh) and credentials named OPENAI_API_KEY, CODEX_API_KEY and CODEX_ACCESS_TOKEN. Our summary lists: A credential in OPENAI_API_KEY; A credential in CODEX_API_KEY.

Does Local Clawsweeper Review access the network?

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

Is Local Clawsweeper Review 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 Local Clawsweeper Review use?

Local Clawsweeper Review 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 Local Clawsweeper Review use?

About 1.4k tokens (SKILL.md is roughly 5.7k 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 Local Clawsweeper Review?

Skills that share tags, products or a category with Local Clawsweeper Review: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Greploop (onyx-dot-app/onyx, 32k stars), GitHub Deep Research (bytedance/deer-flow, 84k stars) and Diagnosing Superpowers Sessions (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Local Clawsweeper Review?

openclaw (a GitHub organization) maintains it in openclaw/clawsweeper, which has 1,996 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 10, 2026.

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