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.
git 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-dogfood)<a href="https://agentmods.dev/commands/f0d010c/stark/stark-dogfood"><img src="https://agentmods.dev/badge/commands/f0d010c/stark/stark-dogfood/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/commands/f0d010c/stark/stark-dogfood"><img src="https://agentmods.dev/badge/commands/f0d010c/stark/stark-dogfood.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 | $0.00000 | $0.00402 |
| Opus 5 | $0.00000 | $0.00201 |
| Sonnet 5 | $0.00000 | $0.00080 |
| Haiku 4.5 | $0.00000 | $0.00040 |
Grade A, and why
stark-dogfood 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 9d 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-dogfood
Use this command when testing whether Stark actually generates better designs, refreshing proof screenshots, creating showcase examples, or turning generated-output failures into guidance changes.
Read, in order:
references/ui-patterns/dogfood-generation-loop.mdreferences/ui-patterns/dogfood-batch-matrix.mdreferences/ui-patterns/design-preflight.mdreferences/ui-patterns/surface-playbook-matrix.mdreferences/ui-patterns/generation-blueprint-contract.mdreferences/ui-patterns/implementation-pattern-library.mdreferences/ui-patterns/browser-qa-matrix.mdreferences/ui-patterns/rendered-quality-gate.mdreferences/ui-patterns/design-quality-metrics.mdreferences/ui-patterns/quality-calibration-ladder.mdreferences/ui-patterns/visual-repair-playbook.mdreferences/ui-patterns/feedback-memory-loop.mdreferences/ui-patterns/design-acceptance-gate.md
Return before generating or testing:
Dogfood plan
- Batch purpose:
- Batch ids:
- Target surfaces:
- Prompts:
- Guidance under test:
- Evidence required:
- Pass bar:
- Gallery rule:
Return after generating/testing:
Dogfood report
- Artifacts:
- Evidence captured:
- Rendered quality gates:
- Scores:
- Repairs applied:
- Feedback memory entries:
- Guidance changes required:
- Gallery-ready screenshots:
- Remaining risk:
Rules:
- Test at least one usable product surface, not only cinematic pages.
- Do not call a screenshot gallery-ready unless desktop and mobile evidence exist and the rendered quality gate is
publicorportfolio. - Treat missing evidence as risk.
- If two generated artifacts repeat the same failure, create a feedback memory entry or update the relevant guidance.
- If the dogfood batch finds no issues, name what evidence makes that credible.
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.
- 9d ago First seen · 57 lines · 0 tokens per session scan A d62e3d8b9e7b
stark-dogfood is a command published in the GitHub repository f0d010c/stark (27 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 402 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
fidelity
Measure how faithfully a clone reproduces a site — pixel-diff plus motion-fidelity into one 0-100 score, a letter grade, a ranked correction plan, and a shareable card.
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.
review
Review the current git diff — auditor selected by --mode (general, security, a11y, deps, perf, tests, contributor-trust, ux) or auto-inferred from the diff when omitted. Pass a PR number to review a specific PR; use --check-followup to re-check a PR after the owner has addressed feedback.