Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/steipete/agent-scripts/clawsweeper-statusnpx skills add steipete/agent-scripts --skill clawsweeper-statusgit clone --depth 1 https://github.com/steipete/agent-scriptsWhat 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 | $0.00023 | $0.00869 |
| Opus 5 | $0.00012 | $0.00434 |
| Sonnet 5 | $0.00005 | $0.00174 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
clawsweeper-status 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 yesterday.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClawSweeper Status
Quick Start
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
Output Contract
Report these sections concisely:
Workers: workflow state, Codex jobs against configured capacity, exact-review queue and target occupancy when available, and active workflow groups. Public queue aggregates remain usable without private target occupancy;occupancy unavailabledoes not mean zero.Queue health: lead with this whenever it is nothealthy. Pending depth on its own is not a verdict — read the split the script prints underneath it:ready/admissiblenear zero while pending is deep means the lane is deliberately holding items back, not stalled.Queue backoff: throttle_retry Nmeans GitHub is rate-limiting; the lane recovers on its own once quota returns.Queue parked (needs operator): review_retry_exhausted Ndoes not self-heal. Parked items retry at 5/10/20 minutes and then wait for a human. Always call these out explicitly.Shed since resetclimbing into the thousands means sustained overload, not a blip.
Publication tail: aggregate pending/ready/backoff/parked/active counts and capacity when available, plus retry and parked reasons. This is separate from the review backlog, not per-target activity; legacy responses without this lane reportunavailable.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.
What ships with it
4 files 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.
- yesterday First seen · 69 lines · 23 tokens per session scan A 35e953794742
clawsweeper-status is a skill published in the GitHub repository steipete/agent-scripts (6,580 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 869 once invoked, about $0.0001 per session on Opus 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…