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-precommit/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-precommit)<a href="https://agentmods.dev/skills/okuzpe/midas-harness/midas-precommit"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-precommit/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-precommit"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-precommit.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 | $0.01529 |
| Opus 5.5 | $0.00026 | $0.00612 |
| Sonnet 5.5 | $0.00013 | $0.00306 |
| Haiku 4.5 | $0.00006 | $0.00153 |
Grade A, and why
midas-precommit 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
midas-precommit — engine quality bar (≥ 80)
Guard + state:
<paths.engine>/templates/skill-state-ritual.md(+AGENTS.md§ Safety / Path resolution). Engine-only. Rubric:docs/precommit-gate.md. Mechanical floor:node scripts/precommit-eval.mjs(staged skill linter + doctor).
Standing pre-commit gate for the midas-harness engine repo. Scores the same harness-fitness dimensions used in full audits. Overall must be ≥ 80 or the verdict is fail — do not commit.
Skill linter: scripts/skill-quality-check.mjs is the mechanical linter for harness/skills/ and harness/agents/ (not ESLint). Precommit runs it with --staged --strict-warns only — warnings on touched skills fail per harness/rules/skill-quality.md. Full-engine 0-warn scan stays in CI (npm test).
Does / Does not
| Does | Does not |
|---|---|
| Abort unless cwd is midas-harness engine | Run on product installs / template trees |
| Run mechanical floor + score 12 dimensions 1–100 | Advance stage or pass lifecycle gates |
Require overall ≥ 80 to verdict=pass |
Replace /midas-align, /midas-doctor, or CI |
Optional freeze under runs/precommits/ (contributors) |
Ship this skill to cli/template / harness/plugins/midas |
Engine guard (hard)
- Confirm engine:
package.json→"name": "midas-harness"andscripts/test.mjsexists. - Otherwise print: ABORT —
/midas-precommitis engine-only; use/midas-align→ STOP.
Procedure
0. Sandbox dry-run (proposed, not forced)
If the staged diff touches harness/skills/** or harness/rules/**, AskQuestion once: run
/midas-sandbox --smoke for the touched skill first, or skip. Default is --smoke. Skip only
when the fixture cannot exercise the change (docs-only skill prose, or the engine-only skill
itself). This is not a mechanical git hook — /midas-sandbox is engine-only, cost-gated
(composer-2.5, never -fast); see sandbox/README.md § Feedback loop. Never block the commit on
the user's answer. After a harness-gap patch, re-run --smoke until grade passes.
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 Changed · +1 lines 151604134d19
- 2mo ago First seen · 125 lines · 65 tokens per session scan A 2ffefeac6cf2
midas-precommit is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 65 tokens to every session and 1,529 once invoked, about $0.0003 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
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…