clawsweeper
Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted…
Skill by ngpestelos-mirrors
Chalk Labs
Need help deploying clawsweeper?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ngpestelos-mirrors-clawsweeper
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: devops
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
clawsweeper- Description
- Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted ClawSweeper-reviewed autofix/automerge, GitHub Actions monitoring, permissions, gates, and manual backfills.
- License
- MIT
- Instructions
- 304 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# ClawSweeper ClawSweeper reviews issues and pull requests across OpenClaw repositories. Its canonical source is [openclaw/clawsweeper](https://github.com/openclaw/clawsweeper). Resolve the actual local checkout instead of assuming its path. ## Start Inspect `git status --short --branch` in the ClawSweeper checkout. Status and report requests stay read-only: use current reports and live read APIs when freshness matters, without pulling or building just to inspect them. For authorized implementation or execution, update a clean task-owned checkout and build only when the selected command needs it. Preserve unrelated edits and other operators' active workflows. Read that checkout's `AGENTS.md` before execution. ## One Bot, One App Use the `clawsweeper` GitHub App and current `CLAWSWEEPER_*` configuration. The source repository owns App setup and permissions. Do not change credentials, permissions, or execution gates for a status request. Review workers propose findings with stripped secret/token environments. Deterministic workflows own comments, labels, and guarded close proposals. A review result does not authorize a separate mutation. ## Hosted Commit Reviews Hosted per-commit reports and commit Check Runs are retired. For the retained offline review of a committed branch, use `pnpm local-review -- --base main`. `$autoreview --mode commit --commit <sha>` remains a separate general-purpose review path. ## Sweep Reports Canonical issue/PR report keys are: ```text records/<repo-slug>/items/<number>.md records/<repo-slug>/closed/<number>.md ``` The Worker store owns current records. Verify freshness before relying on a local copy. Lead with counts, concrete findings, and report links. Do not post unsolicited GitHub comments from report-reading work. PR reports include `reviewFindings` with priority, confidence, repository-relative file, and line range. Public comments show short findings and collapsed review details. Read the durable result rather than inferring coverage from labels. For a simple status request, read existing reports and bounded live workflow state. Use `pnpm run audit` only for a requested full audit. Reconciliation is a separate authorized mutation: bare `pnpm run reconcile` moves/deletes report and work-plan files. Inspect its dry-run only when that maintenance task is requested. Likewise, `apply-decisions` belongs to an explicitly authorized apply workflow, beginning with its dry-run. ## Maintainer Mentions Prefer the supported mention commands: ```text @clawsweeper review @clawsweeper re-review @clawsweeper explain @clawsweeper stop @clawsweeper help ``` `review` and `re-review` request a fresh read-only issue/PR review. `explain` summarizes current status. Review commands can include read-only focus context. Arbitrary freeform questions and action requests do not start repair. Item authors can use `re-review` or `re-run` on their own open items. The router checks current comment identity and repository permissions. Repository membership alone does not establish command authority. `stop` establishes the human-review hold before removing old repair-loop labels. Let that supported command own the transition. Do not remove protection labels manually to reproduce it. Start an authorized comment-routing task with its dry-run: ```bash pnpm run repair:comment-router -- --repo openclaw/openclaw --lookback-minutes 180 ``` The command defaults to dry-run. Scheduled routing stays dry unless `CLAWSWEEPER_COMMENT_ROUTER_EXECUTE=1`. Use `--execute` only for an authorized routing task. Do not toggle or reset gates as generic cleanup. ## Retired Commands And Protected State Repair, autofix, automerge, issue implementation, fix-ci, address-review, rebase, and approve commands are retired. `@clawsweeper status` is also retired. Use `@clawsweeper explain`. The removed repair job creation, validation, dispatch, and executor entrypoints are unavailable. For authorized code repairs and landing, follow the [maintainer workflow](../openclaw-pr-maintainer/SKILL.md). Do not treat a retired command or label as execution or merge authority. Existing `clawsweeper:autofix` and `clawsweeper:automerge` labels still protect items from automatic closure. Preserve those holds, active or unknown owners, leases, locks, receipts, and recovery evidence. Retirement alone authorizes no cleanup or adoption. Remaining `repair:` tooling supports reviews, publication, and maintenance. Its name does not restore repair execution. ## Security Boundary Route vulnerability reports and sensitive disclosures through [OpenClaw security handling](../../../SECURITY.md). A review result or retired repair label does not waive security approval, source trust, required review, or native merge gates. ## Monitoring
From ngpestelos-mirrors/openclaw, MIT.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 12, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ngpestelos-mirrors/openclaw
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.759score
clawsweeper
openclaw
Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted…
SkillAFreshness: A★ 392.9KClaude Code +9 - 0.337score
clawsweeper
Elogic360
Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted…
SkillAFreshness: AClaude Code +9 - 0.337score
clawsweeper
miyataken999
Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted…
SkillAFreshness: AClaude Code +9 - 0.310score
clawsweeper
poppacks
Use for all ClawSweeper work: OpenClaw issue/PR sweep reports, repair jobs, cloud fix PRs, @clawsweeper maintainer mention commands, trusted…
SkillBFreshness: BClaude Code +9
More from ngpestelos-mirrors
- 0.499score
codebase-design
ngpestelos-mirrors
Shared vocabulary for designing deep modules.
SkillBFreshness: BClaude Code +9 - 0.499score
domain-modeling
ngpestelos-mirrors
Build and sharpen a project's domain model.
SkillBFreshness: BClaude Code +9 - 0.499score
prototype
ngpestelos-mirrors
Build a throwaway prototype to answer a design question.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get clawsweeper running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
clawsweeper skill. Agent Mart. https://agentmart.dev/skills/ngpestelos-mirrors-clawsweeper (last updated 2026-10-24)