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-quality-gategit 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-quality-gate)<a href="https://agentmods.dev/commands/f0d010c/stark/stark-quality-gate"><img src="https://agentmods.dev/badge/commands/f0d010c/stark/stark-quality-gate.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 | $0.00472 |
| Opus 5 | $0.00000 | $0.00236 |
| Sonnet 5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
stark-quality-gate 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 5d 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-quality-gate
Use this command when a web UI should be maintained, released, compared across runs, or used as public proof. It turns visual QA into a repeatable local/CI gate instead of a one-off screenshot check.
Read, in order:
references/ui-patterns/qa-evidence-contract.mdreferences/ui-patterns/browser-qa-matrix.mdreferences/ui-patterns/story-driven-qa-harness.mdreferences/ui-patterns/runtime-evidence-regression-contract.mdreferences/ui-patterns/frontend-quality-automation-gate.mdreferences/ui-patterns/performance-budget-contract.mdwhen motion, media, 3D/canvas, charts, large lists, or multiple libraries are presentreferences/ui-patterns/accessibility-interaction-contract.mdwhen custom controls, forms, overlays, keyboard paths, focus, or reduced motion are presentreferences/ux-patterns/task-flow-acceptance-harness.mdwhen the surface is a product workflowreferences/ui-patterns/design-acceptance-gate.md
Output:
Frontend quality automation gate
- Target surface:
- Quality target:
- Gate mode:
- Local command:
- CI command:
- Playwright projects/viewports:
- Story/component harness:
- Visual baselines:
- Interaction flows:
- Accessibility checks:
- Performance/vitals checks:
- Usability/task checks:
- Fixtures and mocks:
- Stabilization/masks:
- Artifact output:
- Failure triage owner:
- Baseline update rule:
- Skipped checks and why:
- Ship decision:
Rules:
- Use advisory gates only for sketches; use blocking or release-blocking gates for public demos, README/gallery screenshots, checkout/trust, and component-library work.
- Prefer role/label/text locators before test IDs; missing accessible names are failures, not selector problems.
- Stabilize clocks, random data, media, animation frames, and generated assets before accepting visual baselines.
- Do not update baselines unless the design changed intentionally or a verified repair changed the evidence.
- Treat lab performance and Web Vitals checks as risk evidence, not field-data proof.
- If a blocking check fails, repair the source issue and re-run the smallest gate that proves the fix.
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.
- 5d ago First seen · 50 lines · 0 tokens per session scan A 40e3934e0eb3
stark-quality-gate 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 472 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
cloudflare-durable-objects:setup
Interactive Durable Objects project initialization. Scaffolds new DO project with proper bindings, migrations, and boilerplate code.
cloudflare-workers:test-setup
Interactive Vitest setup wizard for Cloudflare Workers testing. Configures @cloudflare/vitest-pool-workers, mocks bindings, and creates example tests.
spec-check
Audit GWT acceptance test specs for implementation leakage. Optionally provide a specific file path.
test
Send synthetic webhook events to your local integration — valid, forged and replayed — and verify the handler responds correctly. Works for every provider in the catalog, not just the one with a CLI.
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.
browser
Verify a page or flow in a real browser via Cursor's chrome-devtools MCP. Read-only — Cursor reports; does not modify source files.