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-diff-gatesgit 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-diff-gates)<a href="https://agentmods.dev/skills/okuzpe/midas-harness/midas-diff-gates"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-diff-gates/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-diff-gates"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-diff-gates.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 | $0.00049 | $0.00883 |
| Opus 5.5 | $0.00020 | $0.00353 |
| Sonnet 5.5 | $0.00010 | $0.00177 |
| Haiku 4.5 | $0.00005 | $0.00088 |
Grade A, and why
midas-diff-gates 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
midas-diff-gates — Diff-scoped gate receipts
Guard + state:
<paths.engine>/templates/skill-state-ritual.md(+AGENTS.md§ Safety / Path resolution). Surface:internal(ADR-013) — prefer/close-sprintStep 0.5 path-pass; power-user may still type this slash.
Mechanical test + quality receipts for the current working diff. Run before /close-sprint when
production paths changed. Does not replace /midas-verify (UI/API journeys) or Phase-8 rule
conformance — /close-sprint still owns the independent orchestrate audit.
When to run
| Diff touches | Action |
|---|---|
| Production paths — product source, deploy config, public API contracts | Run both gates; freeze receipts under {paths.cache}/gates/<run>/ |
Engine-only contributor edits (harness/, scripts/, cli/, installer) |
Skip OK — record reason in progress or audit notes |
Docs-only (docs/, markdown rituals, no product source) |
Skip OK — record reason |
Commands
Use the same --run id for both scripts (default: sprint id or timestamp):
node <paths.scripts>/gates/test-gate.mjs --run <id> [--base <ref>]
node <paths.scripts>/gates/quality-gate.mjs --run <id> [--base <ref>]
Receipts:
{paths.cache}/gates/<run>/test.json{paths.cache}/gates/<run>/quality.json
Receipt semantics (isPassingReceipt)
A receipt passes when status is pass or skipped with a non-empty reason.
fail or blocked → blocks /close-sprint until fixed or re-run green.
Procedure
- Read
paths.state+ active sprint; resolve production diff (git diffvs base or staged). - If no production paths → log skip + reason; stop (no receipts required).
- Run
test-gate.mjsthenquality-gate.mjswith the same--runid. - Confirm both receipts exist and satisfy
isPassingReceipt; cite paths in{runs}/sprints/NN-progress.mdor session notes.
Does / Does not
| Does | Does not |
|---|---|
| Freeze deterministic test/quality receipts to cache | Advance stage or pass Phase-8 |
| Block close when gates fail/blocked | Replace /midas-verify or UI proof |
| Allow explicit skip for non-production diffs | Run LLM conformance audit |
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 · 77 lines · 49 tokens per session scan A 5dafdc3ba1a6
midas-diff-gates is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 883 once invoked, about $0.0002 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
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
review-checklist
The team's checklist for reviewing a change to linkcheck. Use before you commit or open a pull request.
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.