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 okuzpe/midas-harness --skill midas-sweepgit clone --depth 1 https://github.com/okuzpe/midas-harnessWrote 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/okuzpe/midas-harness/midas-sweep)<a href="https://agentmods.dev/skills/okuzpe/midas-harness/midas-sweep"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-sweep/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/okuzpe/midas-harness/midas-sweep"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-sweep.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 | $0.00065 | $0.01893 |
| Opus 5 | $0.00032 | $0.00946 |
| Sonnet 5 | $0.00013 | $0.00379 |
| Haiku 4.5 | $0.00006 | $0.00189 |
Grade A, and why
midas-sweep 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
midas-sweep — Hygiene, cleanup & dead-flow detection
Guard + state:
<paths.engine>/templates/skill-state-ritual.md(+AGENTS.md§ Safety / Path resolution). Surface:internal(ADR-013) — prefer/midas-hygiene//close-sprint/ adopt path-pass; power-user may still type this slash. No stage precondition — runs anytime. No{product}/+ no app source → limit to harness/docs consistency. Record shape:<paths.engine>/templates/sweep-record.md. Tally:<paths.engine>/templates/audit-checklists.md§ Parseable tally lines.
Standing hygiene pass (not a phase gate): find dead weight and drift, report ranked by severity, apply safe cleanups only with explicit user confirmation. Unlike /midas-doctor (adapters) or /midas-tribunal (decisions), sweep asks what on disk is unused, unreachable, or lying?
Recommended checkpoints: prefer /midas-hygiene (primary) for product scopes; this body is the path-pass procedure. Non-advancing — never changes stage.
Does / Does not
| Does | Does not |
|---|---|
Index, classify, rank, freeze {runs}/sweeps/sweep-NN.md |
Advance stage or pass gates |
Optional --fix after numbered plan + explicit yes |
Silently delete or rewrite business/architecture decisions |
Emit MIDAS_SWEEP_RESULT tally |
Replace /midas-hygiene, /midas-security-audit, /midas-tribunal, /midas-doctor, or /close-sprint |
Scope & depth
Scope (default all for power-user slash; /midas-hygiene always passes product):
code— source, routes, imports, playbooks vssrc/*docs—{product}/*, broken links, stale OPEN questionsproduct—code+docsonly (excludes harness-drift). Prefer this from/midas-hygiene.harness— state vs sprint/gate files, stale audits (power-user / install health — not product hygiene)all— every row including harness (legacy; do not use from/midas-hygiene)
When scope is product, code, or docs: set harness_drift=0 in the tally (do not hunt harness-drift).
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.
- 4d ago Changed 6d8fd21a0241
- 9d ago First seen · 106 lines · 65 tokens per session scan A f4183f68c4eb
midas-sweep is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,893 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…