Borrowing it
Nothing to install: this file belongs to okuzpe/midas-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/okuzpe/midas-harness/main/.agents/skills/midas-hygiene/SKILL.mdgit 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-hygiene)<a href="https://agentmods.dev/skills/okuzpe/midas-harness/midas-hygiene"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-hygiene/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-hygiene"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-hygiene.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 | $0.00073 | $0.01171 |
| Opus 5 | $0.00036 | $0.00585 |
| Sonnet 5 | $0.00015 | $0.00234 |
| Haiku 4.5 | $0.00007 | $0.00117 |
Grade A, and why
midas-hygiene 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 5d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
midas-hygiene — product repo cleanup
Guard + state:
<paths.engine>/templates/skill-state-ritual.md(+AGENTS.md§ Safety / Path resolution). Surface:primary— human-typed; parents (/close-sprintStep 0) path-pass this body (read + run — not Skill-tool). Scope: product code +{product}/*only. Never.harness/engineadapters, doctor, or align.
Standing repo hygiene (not a phase gate): find dead weight in the product tree, report, optionally fix with explicit confirm. Complements Layer C Sync (/midas-doctor, /midas-align) — those are install/adapter health, not product dead-flow.
Does / Does not
| Does | Does not |
|---|---|
Path-pass midas-sweep with scope product (or code / docs) |
Run sweep scope harness or legacy all (includes harness) |
Path-pass midas-lean-review when mode is lean or fat-diff all |
Advance stage or pass Phase-8 alone |
Reuse {runs}/sweeps/sweep-NN.md + optional lean-NN.md |
Replace /close-sprint, tribunal, security, or doctor |
Modes (AskQuestion or args)
| Mode / arg | Path-pass |
|---|---|
all (default) |
sweep product; if working-tree diff is large/fat UI-feature, also lean-review (--scope diff) |
dead-flows / code |
sweep code |
docs |
sweep docs |
lean |
lean-review only (--scope diff default) |
report-only |
same as chosen mode without --fix / apply |
--fix → forward to sweep --fix only after the report; lean apply only if the human asks after the delete-list.
Procedure
- Read
paths.state. Resolve mode from args or one AskQuestion (defaultall). - Sweep leg (unless mode=
leanonly): Read and follow<paths.engine>/skills/midas-sweep/SKILL.mdwith scopeproduct(orcode/docsper mode). Never passharnessorall. Expectharness_drift=0in the tally for product scopes (R6). - Lean leg: When mode is
lean, or mode isalland the diff is fat (many files / UI feature), path-pass<paths.engine>/skills/midas-lean-review/SKILL.md(optional--freeze). - Report combined summary; recommended next =
/close-sprintwhen in an active sprint, else/midas-status. - Optional fix: only with explicit human OK (sweep
--fix/ lean apply). Prefer archive over hard delete.
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.
- 5d ago Changed ef08fc909ec9
- 10d ago First seen · 82 lines · 73 tokens per session scan A b5ea3964eaa2
midas-hygiene is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,171 once invoked, about $0.0004 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
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
gsd-ns-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.
dorodango
Polishes working code through successive quality passes in fresh subagents. Use after tests pass when code needs multi-dimension refinement before release.