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-regenerate)<a href="https://agentmods.dev/commands/f0d010c/stark/stark-regenerate"><img src="https://agentmods.dev/badge/commands/f0d010c/stark/stark-regenerate.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 5.1 | $0.00000 | $0.00703 |
| Opus 5 | $0.00000 | $0.00351 |
| Sonnet 5 | $0.00000 | $0.00141 |
| Haiku 4.5 | $0.00000 | $0.00070 |
Grade A, and why
stark-regenerate 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 7d 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.
This is a copy
88% identical to stark-director — 94 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
/stark-regenerate
Use this command when the user wants another attempt at a design after critique, or asks Stark to generate better/original alternatives instead of repeating the same visual pattern.
Read, in order:
references/ui-patterns/feedback-memory-loop.mdreferences/ui-patterns/design-preflight.mdreferences/ui-patterns/taste-calibration-system.mdreferences/ui-patterns/variant-selection-loop.mdreferences/ui-patterns/style-diversity-matrix.mdreferences/ui-patterns/product-intent-matrix.mdreferences/ui-patterns/surface-playbook-matrix.mdreferences/ui-patterns/generation-blueprint-contract.mdbefore implementation for serious web UIreferences/ui-patterns/prompt-to-build-compiler.mdimmediately before serious code generationreferences/ui-patterns/implementation-pattern-library.mdwhen a known product surface matchesreferences/ui-patterns/pattern-selection.mdreferences/ui-patterns/composition-system.mdreferences/ui-patterns/layout-precision-system.mdreferences/ui-patterns/typography-systems.mdreferences/ui-patterns/font-selection-matrix.mdreferences/ui-patterns/copy-system.mdreferences/ui-patterns/asset-realism-matrix.mdwhen media/proof assets matterreferences/ui-patterns/motion-pattern-atlas.mdandreferences/ui-patterns/motion-library-playbooks.mdwhen motion mattersreferences/ui-patterns/library-orchestration-system.mdwhen multiple libraries or capabilities are involvedreferences/ux-patterns/usability-scenario-testing.mdfor serious product UIreferences/ui-patterns/implementation-review-loop.mdreferences/ui-patterns/rendered-quality-gate.mdwhen rendered or screenshot evidence existsreferences/ui-patterns/qa-evidence-contract.mdreferences/ui-patterns/browser-qa-matrix.mdreferences/ui-patterns/visual-repair-playbook.mdreferences/ui-patterns/design-acceptance-gate.md
Return before implementation:
Regeneration brief
- User critique remembered:
- Future ban:
- Future preference:
- Stress test:
- Surface/user mode:
- Product job:
- Quality target:
- Variant A:
- Variant B:
- Variant C:
- Scorecard:
- Selected variant:
- Rejected variants:
- Borrowed details:
- Product object:
- Surface playbook:
- Generation blueprint:
- Prompt-to-build compiler:
- Implementation pattern:
- Structural pattern:
- Typography/copy:
- Motion/library ownership:
- Usability/state contract:
- Responsive/adaptive strategy:
- QA probes:
After implementation or audit, return:
Regeneration report
- What changed:
- Feedback memory applied:
- Selected variant preserved:
- Design-to-code drift:
- Rendered quality:
- Evidence captured:
- Hard fails fixed:
- Acceptance gate:
- Remaining risk:
Rules:
- Preserve the user's exact critique wording before normalizing it.
- Do not generate variants that only swap color/font/theme.
- Do not merge variants into a collage.
- Do not repeat an active feedback-memory ban unless the report explains why it no longer applies.
- Treat missing rendered evidence as uncertain, not passing.
- Apply at least one high-impact repair when evidence shows a repeat failure.
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.
- 7d ago First seen · 88 lines · 0 tokens per session scan A 803c6647234b
stark-regenerate is a command published in the GitHub repository f0d010c/stark (26 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 703 tokens. A static security scan graded it A with 0 findings. It is 88% identical to stark-director, differing in 94 lines, and is treated as a copy.
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.
accessibility-specialist
Use when a screen might fail WCAG. Unlabeled inputs, no keyboard path, contrast below AA, missing landmarks, broken heading order, screen reader gaps, or a request for an a11y review or EU Accessibility Act check.
design-brief
Use when a design request is broad or unclear and you do not know which specialist it needs. Reads the brief, routes it to the right expertise, and returns structured guidance.