skills/clawsweeper-status/SKILL.md
ClawSweeper status: URLs, workflow health, active workers, ops snapshot.
npx skillsauth add steipete/agent-scripts clawsweeper-statusInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Run the bundled status script first:
/Users/steipete/Projects/agent-scripts/skills/clawsweeper-status/scripts/clawsweeper-status.sh
Useful options:
# Last 10 hours for the default target repo, openclaw/openclaw
/Users/steipete/Projects/agent-scripts/skills/clawsweeper-status/scripts/clawsweeper-status.sh --hours 10
# A different target repo
/Users/steipete/Projects/agent-scripts/skills/clawsweeper-status/scripts/clawsweeper-status.sh --repo openclaw/clawhub
# More rows per activity section
/Users/steipete/Projects/agent-scripts/skills/clawsweeper-status/scripts/clawsweeper-status.sh --limit 15
Report these sections concisely:
Workers: workflow state, Codex jobs against configured capacity, exact-review queue and target occupancy, and active workflow groups.Recently merged: merged PR URLs plus one-line titles.Recently reviewed: ClawSweeper/Codex review comment URLs plus one-line comment summary.Recently commented: other recent ClawSweeper comment URLs plus one-line comment summary.Recently closed: closed issue/PR URLs plus one-line titles.If the script returns no rows for a section, say none found in window.
Prefer the script because it uses bounded API calls:
openclaw/clawsweeper;Do not browse the web for these checks. Use gh directly.
pending workflow runs as concurrency waiters, not queued Codex jobs.gh run list results with the default recent-run list when numbers disagree.tools
Claude Code-only work routing: delegate implementation, fixing, exploratory subagents, rebasing, and PR merging/landing to Codex CLI while Claude specifies, decides, reviews, and verifies. Direct hands-on delegation requires ANTHROPIC_BASE_URL to be unset or neither loopback nor gorillaclaw.sheep-coho.ts.net. Codex-backed autoreview is always allowed and preferred, independent of environment.
development
Codex 1M context: direct OpenAI Responses API inference, safe Sol/Terra/Luna input headroom, Keychain delivery, and Mac fleet rollout.
data-ai
Remote Macs: MacBook, Mac Studio, clawmac, megaclaw, Tailscale, SSH, OpenClaw.
development
REQUIRED before ANY `op` command or whenever a task needs an API key, token, password, credential, or secret (OPENAI_API_KEY, ANTHROPIC_API_KEY, deploy tokens, live-test keys). Prompt-free 1Password service-account reads; wrong invocations spam macOS dialogs.