Research & Analysis🌐universal
ClawSweeper
ClawSweeper scans all issues and PRs and suggest what we can close, and why. It runs every PR / Issue once a week.
Quick Start
Install this Skill
npx skills add openclaw/clawsweeper# ClawSweeper ClawSweeper is the conservative OpenClaw maintenance bot for `openclaw/openclaw`. It keeps one markdown report per open issue or PR, publishes one durable Codex automated review comment when useful, and only closes items when the evidence is strong. ## Guardrails ClawSweeper may propose a close only when the item is clearly one of these: - implemented on current `main` - not reproducible on current `main` - better suited for ClawHub skill/plugin work than core - duplicate or superseded by a canonical issue/PR - concrete but not actionable in this source repo - incoherent enough that no action can be taken - stale issue older than 60 days with too little data to verify Maintainer-authored items are never auto-closed. Everything else stays open. ## Dashboard Last dashboard update: Apr 26, 2026, 06:54 UTC ### Current Run <!-- clawsweeper-status:start --> **Workflow status** Updated: Apr 26, 2026, 06:54 UTC State: Apply in progress Starting apply/comment-sync run for up to 20 fresh all closes. Existing Codex automated review comments are updated in place; checkpoints commit every 50 fresh closes; close delay is 2000ms; sync-comments-only=false; item numbers=all. Run: [https://github.com/openclaw/clawsweeper/actions/runs/24950576448](https://github.com/openclaw/clawsweeper/actions/runs/24950576448) <!-- clawsweeper-status:end --> ### Queue | Metric | Count | | --- | ---: | | Open issues in [openclaw/openclaw](https://github.com/openclaw/openclaw) | 4210 | | Open PRs in [openclaw/openclaw](https://github.com/openclaw/openclaw) | 3927 | | Open items total | 8137 | | Reviewed files | 7919 | | Unreviewed open items | 218 | | Archived closed files | 11378 | ### Review Outcomes | Metric | Count | | --- | ---: | | Fresh reviewed issues in the last 7 days | 4099 | | Proposed issue closes | 79 (1.9% of reviewed issues) | | Fresh reviewed PRs in the last 7 days | 3777 | | Proposed PR closes | 68 (1.8% of reviewed PRs) | | Fresh verified reviews in the last 7 days | 7876 | | Proposed closes awaiting apply | 147 (1.9% of fresh reviews) | | Closed by Codex apply | 8886 | | Failed or stale reviews | 43 | ### Cadence | Metric | Coverage | | --- | ---: | | Hourly cadence coverage | 362/940 current (578 due, 38.5%) | | Hourly hot item cadence (<7d) | 362/940 current (578 due, 38.5%) | | Daily cadence coverage | 4892/4989 current (97 due, 98.1%) | | Daily PR cadence | 3282/3360 current (78 due, 97.7%) | | Daily new issue cadence (<30d) | 1610/1629 current (19 due, 98.8%) | | Weekly older issue cadence | 1985/1990 current (5 due, 99.7%) | | Due now by cadence | 898 | ### Audit Health <!-- clawsweeper-audit:start --> Last audit: Apr 26, 2026, 06:52 UTC Status: **Action needed** | Metric | Count | | --- | ---: | | Scan complete | yes | | Open items seen | 8155 | | Missing eligible open records | 5 | | Missing maintainer-authored open records | 72 | | Missing protected open records | 0 | | Missing recently-created open records | 142 | | Archived records that are open again | 0 | | Stale item records | 7 | | Duplicate records | 0 | | Protected proposed closes | 2 | | Stale reviews | 41 | | Item | Category | Title | Detail | | --- | --- | --- | --- | | [#66922](https://github.com/openclaw/openclaw/issues/66922) | Missing eligible open | [Bug]: xAI grok reasoning models (grok-4-1-fast-reasoning) ignore workspace IDENTITY.md behavioral rules at 0% compliance rate | eligible | | [#66923](https://github.com/openclaw/openclaw/issues/66923) | Missing eligible open | OpenClaw Model Registry: GPT-4.1 family passes through unmanaged | eligible | | [#68655](https://github.com/openclaw/openclaw/issues/68655) | Missing eligible open | bug(web-ui): streaming markdown flickers — full DOM replacement on every token via unsafeHTML | eligible | <!-- clawsweeper-audit:end --> ### Latest Run Activity Latest review: Apr 26, 2026, 06:44 UTC. Latest close: Apr 26, 2026, 06:53 UTC. Latest comment sync: Apr 26, 2026, 06:53 UTC. | Window | Reviews | Close decisions | Keep-open decisions | Failed/stale reviews | Closed | Comments synced | Apply skips | | --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | | Last 15 minutes | 64 | 21 | 43 | 0 | 72 | 72 | 0 | | Last hour | 773 | 203 | 570 | 2 | 195 | 168 | 1 | | Last 24 hours | 10417 | 2390 | 8027 | 56 | 5299 | 1173 | 155 | <details> <summary>Recently Reviewed (latest 10)</summary> <br> | Item | Title | Outcome | Status | Reviewed | | --- | --- | --- | --- | --- | | [#51455](https://github.com/openclaw/openclaw/issues/51455) | bug: pdf extraction fallback renderer omits standardFontDataUrl and emits PDF.js warnings in Node | [keep_open / kept_open](https://github.com/openclaw/clawsweeper/blob/main/items/51455.md) | complete | Apr 26, 2026, 06:42 UTC | | [#46472](https://github.com/openclaw/openclaw/pull/46472) | fix(feishu): add WebSocket heartbeat config to prevent silent disconnection | [keep_open / kept_open](https://github.com/openclaw/clawsweeper/blob/main/items ... (truncated)
Repository
747stars
70forks
Details
Related Skills
More research & analysis skills you might like
pr-improver
Research & AnalysisRuns an autonomous review-and-fix improvement loop over the current branch's changes until a PR review comes back clean, scoped mechanically to the directories the branch touched. Reviews are performed by an installed PR-review skill (default: pr-review-toolkit's review-pr). Use to fix review findings on a branch before opening or updating a pull request ('clean up this branch', 'fix this PR until review passes', 'run review-and-fix on my changes'). NOT for a one-time review — run the PR-review skill directly.
🤖claude🌐universal
7.5k
643
View
code-improver
Research & AnalysisRuns an autonomous review-and-fix improvement loop over any code target — a skill, plugin, module, or directory — using a reviewer the user names: any installed skill or agent. Keeps a cross-round findings ledger, escalates when fixes stop converging, and guards scope mechanically. Use when asked to 'improve this code until review passes', 'run an improvement loop with <reviewer>', or to iterate review-and-fix with a specific reviewer. For skills prefer the skill-improver entry; for a branch prefer pr-improver.
🤖claude🌐universal
7.5k
643
View
skill-improver
Research & AnalysisRuns an autonomous review-and-fix improvement loop over a Claude Code skill until a review comes back clean, with a cross-round findings ledger, escalation when fixes stop converging, and a mechanical scope guard. Reviews are performed by the plugin-dev skill-reviewer agent. Use to fix skill quality issues, iteratively refine a skill, or resume a loop after an escalation ('fix my skill', 'improve this skill until it passes review', 'skill improvement loop'). NOT for a one-time review — use the plugin-dev skill-reviewer agent directly.
🤖claude🌐universal
7.5k
643
View
audit-augmentation
Research & AnalysisAugments Trailmark code graphs with external audit findings from SARIF static analysis results, weAudit annotation files, and version-gated Trailmark 0.4.x binary-analysis graph exports. Maps findings to graph nodes by file and line overlap, creates severity-based subgraphs, and enables cross-referencing findings with pre-analysis data (blast radius, taint, etc.). Use when projecting SARIF results onto a code graph, overlaying weAudit annotations, importing binary graph findings, cross-referencing Semgrep, CodeQL, or binary-analysis findings with call graph data, or visualizing audit findings in the context of code structure.
🌐universal
7.5k
643
View