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 skills add shinpr/nautilus --skill recipe-refine-visualsgit clone --depth 1 https://github.com/shinpr/nautilusWrote 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/skills/shinpr/nautilus/recipe-refine-visuals)<a href="https://agentmods.dev/skills/shinpr/nautilus/recipe-refine-visuals"><img src="https://agentmods.dev/badge/skills/shinpr/nautilus/recipe-refine-visuals/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/skills/shinpr/nautilus/recipe-refine-visuals"><img src="https://agentmods.dev/badge/skills/shinpr/nautilus/recipe-refine-visuals.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 | $0.00032 | $0.00338 |
| Opus 5 | $0.00016 | $0.00169 |
| Sonnet 5 | $0.00006 | $0.00068 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
recipe-refine-visuals 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
Context: Refine the Visual Tokens in docs/product/design/brand-direction.md after recipe-blueprint has created an initial set.
This side workflow applies when a human with design judgment explicitly requests refinement of the auto-derived token set.
Required Skills [LOAD BEFORE EXECUTION]
- [LOAD IF NOT ACTIVE]
blueprint-standards— brand-direction template and Visual Token structure - [LOAD IF NOT ACTIVE]
design-perspective— accessibility and persona-aware design review
Workflow
- Read
docs/product/design/brand-direction.md - Review current Visual Tokens against design principles, personas, and prototype learnings
- Verify:
- text-on-surface contrast ratio is at least 4.5:1 for normal text
- heading text is at least 1.25x the body size in the primary hierarchy step
- spacing tokens form a consistent increasing scale without reversals
- Apply exact overrides supplied by the user and mark the source as
expert-refined - When the request requires a new design choice, present only that choice and its rationale; update the file after the user confirms it
Scope Boundaries
Included: colors, typography, spacing, radius, shadow values Not included: redesigning the entire blueprint or introducing implementation-specific component APIs
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +2 lines 61ccfbb0d948
- 10d ago First seen · 31 lines · 32 tokens per session scan A 68f595a0262f
recipe-refine-visuals is a skill published in the GitHub repository shinpr/nautilus (4 stars, last pushed 8d ago), licensed MIT. It adds 32 tokens to every session and 338 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
blueprint-standards
Defines structural design artifact formats — information architecture, user flows, content model, brand direction, and AI interaction model. Use when creating or reviewing structural design documents that precede prototype generation.
recipe-blueprint
Define structural design foundation — information architecture, user flows, content model, brand direction, and AI interaction model — from validated opportunities and hypotheses.
design-perspective
Integrates design principles, WCAG 2.2 AA accessibility, persona context, and state design into product decisions. Use when reviewing UX decisions, checking accessibility, applying design principles, or ensuring state coverage in acceptance criteria.
prototype-guide
Generates self-contained HTML prototypes with design context from project files. Read design principles, personas, and hypothesis files, then produce a working prototype for Usability and Value risk validation. Use when creating prototypes or validating through tangible artifacts.
recipe-refine-visuals
Optional side-workflow for design experts to refine Concrete Tokens in brand-direction.md when a named downstream consumer needs reproducible values.
productspec
Use when implementing, reviewing, planning, or changing work governed by a Product Spec. Treat .product-spec.md files as the product contract for the work.