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-qagit 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-qa)<a href="https://agentmods.dev/skills/okuzpe/midas-harness/midas-qa"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-qa/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-qa"><img src="https://agentmods.dev/badge/skills/okuzpe/midas-harness/midas-qa.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 | $0.00072 | $0.01184 |
| Opus 5.5 | $0.00029 | $0.00474 |
| Sonnet 5.5 | $0.00014 | $0.00237 |
| Haiku 4.5 | $0.00007 | $0.00118 |
Grade A, and why
midas-qa 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
midas-qa — Ad-hoc branch QA
Guard + state:
<paths.engine>/templates/skill-state-ritual.md(+AGENTS.md§ Safety / Path resolution). Surface:internal(ADR-013) — prefer Phase 7 path-pass; power-user may still type this slash.
Quick QA on what changed — not the formal sprint gate. /midas-verify remains required before /close-sprint for UI sprints.
Does / Does not
| Does | Does not |
|---|---|
| Smoke-test routes/screens touched by the diff | Write tests to {product}/ |
Optional evidence in {runs}/qa/qa-adhoc-*.md |
Emit MIDAS_VERIFY_RESULT (not gate-parsed) |
| Report pass/fail/skip + console errors in chat | Auto-fix failures or pass Phase 8 |
Prerequisites
- Dev server running (or user starts after port detect)
- Web: agent-browser CLI
- Native (diff touches
android/,ios/,app/): Maestro MCP + emulator/simulator
Pre-check (cross-platform):
command -v agent-browser >/dev/null 2>&1 && echo ready || echo missing # POSIX
Get-Command agent-browser -ErrorAction SilentlyContinue # PowerShell
where.exe agent-browser # cmd
Missing → report install instructions and stop (web QA cannot run).
Procedure
1. Determine scope
- PR:
gh pr view <n> --json files -q '.files[].path' - Current/empty:
git diff --name-only main...HEAD - Named branch:
git diff --name-only main...<branch>
2. Map files → routes/surfaces
| Pattern | Surface |
|---|---|
src/app/**, app/** |
URL paths |
src/pages/** |
Page routes |
src/components/**, components/** |
Pages importing them |
android/**, ios/**, app.json |
Native — Maestro list_devices + launchApp |
| Layout/global CSS | Homepage + one inner page minimum |
3. Port and server
Default port from package.json / .env / architecture (usually 3000). If not listening, ask user to start (no auto-start without confirm). agent-browser open http://localhost:<PORT>.
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 · 119 lines · 72 tokens per session scan A 3404fd364925
midas-qa is a skill published in the GitHub repository okuzpe/midas-harness (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,184 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
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.