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 skills add nirecom/agents --skill sweep-supervisor-stategit clone --depth 1 https://github.com/nirecom/agentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nirecom/agents/sweep-supervisor-state)<a href="https://agentmods.dev/skills/nirecom/agents/sweep-supervisor-state"><img src="https://agentmods.dev/badge/skills/nirecom/agents/sweep-supervisor-state/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nirecom/agents/sweep-supervisor-state"><img src="https://agentmods.dev/badge/skills/nirecom/agents/sweep-supervisor-state.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00015 | $0.00345 |
| Opus 5.5 | $0.00006 | $0.00138 |
| Sonnet 5.5 | $0.00003 | $0.00069 |
| Haiku 4.5 | $0.00002 | $0.00034 |
Grade A, and why
sweep-supervisor-state 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 1mo ago.
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.
What it actually says
/sweep-supervisor-state
Remove the escape-hatch records that leaking test suites wrote into real supervisor state files under ~/.workflow-plans/.
Usage
Invoke bin/sweep-supervisor-state.sh with forwarded arguments.
Nothing is written unless --apply is passed — this member of the /sweep family is deliberately non-destructive by default, because it edits a governance audit trail rather than a regenerable derivative.
| Flag | Effect |
|---|---|
--apply |
Write the changes; the pre-modification files and a manifest.json are copied to a timestamped backup directory first. |
--ci-mode |
Emit a single-line JSON summary instead of prose. |
--list-signatures |
Print the reason allowlist and exit. |
--session <SID> |
Narrow the target set to one session. |
When to use
Run after a test suite is found writing into the live plans dir, or when bin/check-plans-dir-isolation.sh reports W-candidates that already ran.
Preview with a flagless run first, confirm the reported records are test fixtures, then re-run with --apply.
Guard
Sessions still in flight (alert_phase=pending, audit_phase pending or in progress, updated within 24h, or the current session) are always skipped. There is no override flag; --session narrows the target set but never relaxes the guard.
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.
- 1mo ago First seen · 35 lines · 15 tokens per session scan A d594b320a7b1
sweep-supervisor-state is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 345 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…