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-lean-reviewgit 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-lean-review)<a href="https://agentmods.dev/skills/okuzpe/midas-harness/midas-lean-review"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-lean-review/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-lean-review"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-lean-review.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 | $0.01132 |
| Opus 5.5 | $0.00029 | $0.00453 |
| Sonnet 5.5 | $0.00015 | $0.00226 |
| Haiku 4.5 | $0.00007 | $0.00113 |
Grade A, and why
midas-lean-review 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 2mo 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
midas-lean-review — What to delete (over-engineering only)
Guard + state:
<paths.engine>/templates/skill-state-ritual.md(+AGENTS.md§ Safety / Path resolution). Surface:internal(ADR-013) — prefer/close-sprint/ fat-diff path-pass; power-user may still type this slash. Rule:<paths.engine>/rules/lean-ladder.md. Tally shape:<paths.engine>/templates/audit-checklists.md.
Standing complexity review (not a phase gate): hunt unnecessary code in the working tree / named
paths. Report a delete-list; do not apply fixes unless the user explicitly asks after the report.
Correctness, security, and performance bugs are out of scope — route those to normal review,
/midas-security-audit, or /close-sprint.
Inspired by Ponytail's review format; Midas-owned procedure and freeze path.
Does / Does not
| Does | Does not |
|---|---|
Rank over-engineering findings (delete / stdlib / native / yagni / shrink) |
Advance stage or pass gates |
Optional {runs}/lean/lean-NN.md with --freeze |
Silently rewrite the tree |
Emit MIDAS_LEAN_RESULT when freezing |
Replace /midas-sweep, /midas-qa, or Phase-8 audit |
Scope
--scope |
Default target |
|---|---|
diff (default) |
git diff against the default branch (or staged+unstaged if no upstream) |
paths |
Only user-named paths |
repo |
Broad pass — cap findings; prefer diff for sprint work |
Finding tags (one line each)
path:Lstart-Lend: tag: what to cut. Replacement.
| Tag | Meaning |
|---|---|
delete |
Dead / unused flexibility / speculative feature → nothing replaces it |
stdlib |
Hand-rolled thing the standard library already does — name the API |
native |
Dep or code doing what the platform already does — name the feature |
yagni |
Abstraction with one implementation, config nobody sets, layer with one caller |
shrink |
Same logic, fewer lines — show the shorter form |
Never flag the lean minimum test/assert self-check as bloat. Never propose cutting trust-boundary validation, security, or accessibility required by sibling rules.
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.
- 2mo ago First seen · 90 lines · 73 tokens per session scan A 5e724dc6353e
midas-lean-review is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,132 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…