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 agentmods add commands/f0d010c/stark/stark-qagit clone --depth 1 https://github.com/f0d010c/starkWrote 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/commands/f0d010c/stark/stark-qa)<a href="https://agentmods.dev/commands/f0d010c/stark/stark-qa"><img src="https://agentmods.dev/badge/commands/f0d010c/stark/stark-qa.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00290 |
| Opus 5 | $0.00000 | $0.00145 |
| Sonnet 5 | $0.00000 | $0.00058 |
| Haiku 4.5 | $0.00000 | $0.00029 |
Grade A, and why
stark-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 3d 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.
What it actually says
/stark-qa
Use this command to require proof before calling a UI "good."
Read:
references/ui-patterns/qa-evidence-contract.mdreferences/ui-patterns/browser-qa-matrix.mdreferences/ui-patterns/visual-qa-protocol.mdreferences/ui-patterns/visual-qa-workflow.mdreferences/ui-patterns/rendered-quality-gate.mdwhen rendered or screenshot evidence existsreferences/ui-patterns/visual-repair-playbook.mdreferences/ui-patterns/design-quality-metrics.mdreferences/ui-patterns/design-acceptance-gate.md
Output:
QA evidence contract
- Surface:
- Risk level:
- Evidence required:
- Evidence captured:
- Browser probes:
- Hard fails:
- Fix applied:
- Re-check:
- Rendered quality:
- Acceptance gate:
- Missing evidence:
- Remaining risk:
Rules:
- Treat missing evidence as uncertain, not passing.
- Use desktop/mobile, console, interaction, reduced-motion, nonblank media/canvas, and state evidence according to surface risk.
- If a hard fail appears, fix it and re-check the same evidence before final delivery.
- If the acceptance gate is below the requested design level, continue with one required repair.
- Do not claim "looks good" without browser/runtime/screenshot evidence when such evidence is available.
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.
- 3d ago First seen · 41 lines · 0 tokens per session scan A bbd9e136e1b6
stark-qa is a command published in the GitHub repository f0d010c/stark (25 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 290 tokens. 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 2026-08-30.
Other commands, from other repositories
OPSX: Explore
Enter explore mode - think through ideas, investigate problems, clarify requirements.
anti-slop-designer
Use when a UI looks machine-made rather than decided. Violet gradients, glassmorphism everywhere, identical cards in a grid, untouched shadcn or Material defaults, emoji bullets, or copy stuffed with seamless and unlock.
design-grill
Use when a design keeps getting reinvented every session. Interviews you until you share one understanding, then writes the vocabulary and the binding decisions into the repo so they survive the next context window.
database-setup
Use when a project needs to store data and has no database yet. Setting up Supabase, creating tables, writing queries, and connecting them to the frontend. Written for designers.
deploy-to-vercel
Use when a project runs locally but is not on the internet yet, or a Vercel deploy is failing. First deploy, build errors, environment variables, custom domain.
environment-setup
Use when handling secrets and config. What .env files are, which filename to use, what must never reach GitHub, and why a key works locally but not in production.