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-qualitygit 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)<a href="https://agentmods.dev/commands/f0d010c/stark/stark-quality"><img src="https://agentmods.dev/badge/commands/f0d010c/stark/stark-quality.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 | $0.00229 |
| Opus 5 | $0.00000 | $0.00114 |
| Sonnet 5 | $0.00000 | $0.00046 |
| Haiku 4.5 | $0.00000 | $0.00023 |
Grade A, and why
stark-quality 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 4d 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
Score a UI, design brief, or generated implementation against Stark's design quality metrics.
Use references/ui-patterns/design-quality-metrics.md, references/ui-patterns/quality-calibration-ladder.md, references/ui-patterns/qa-evidence-contract.md, references/ui-patterns/rendered-quality-gate.md when rendered or screenshot evidence exists, references/ui-patterns/visual-repair-playbook.md, and references/ui-patterns/design-acceptance-gate.md.
Output:
Design quality report
- Surface/user mode:
- Scores: product specificity _, state coverage _, hierarchy _, originality _, typography _, motion _, assets _, accessibility _, responsive _, implementation _
- Hard fails:
- Evidence:
- Rendered quality:
- First repair:
- Fix applied after critique:
- Acceptance gate:
- Remaining risk:
Rules:
- Treat missing evidence as uncertain, not passing.
- Fix hard fail gates before polish.
- Do not stop below the requested level: functional, good, polished, high-craft, or portfolio.
- Do not improve a score by adding decoration.
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.
- 4d ago First seen · 28 lines · 0 tokens per session scan A a6e6255501e1
stark-quality 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 229 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
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-enforce
Use when code has drifted off the design system. Raw hex values and pixel numbers written where a token already exists, one-off components, library defaults left untouched. Finds every bypass and fixes it.
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.
design-triage
Use when a dwic audit report is full of findings and there is no plan. Ranks them into an order someone can work through, then works through it.
debug-helper
Use when something is broken and you need it diagnosed. A build failure, a runtime crash, a blank page, an unreadable error message, or behaviour that is simply wrong. Gives one exact fix, not a list of things to try.
auth-implementation
Use when a project needs real working login and signup rather than advice. Wiring up Clerk or Supabase Auth, protecting routes, handling sessions. Writes actual code, not guidance.