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 infolog-io/skills --skill atomic-brandgit clone --depth 1 https://github.com/infolog-io/skillsWrote 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/infolog-io/skills/atomic-brand)<a href="https://agentmods.dev/skills/infolog-io/skills/atomic-brand"><img src="https://agentmods.dev/badge/skills/infolog-io/skills/atomic-brand/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/infolog-io/skills/atomic-brand"><img src="https://agentmods.dev/badge/skills/infolog-io/skills/atomic-brand.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 | $0.00154 | $0.01642 |
| Opus 5 | $0.00077 | $0.00821 |
| Sonnet 5 | $0.00031 | $0.00328 |
| Haiku 4.5 | $0.00015 | $0.00164 |
Grade A, and why
atomic-brand 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
atomic-brand
Purpose
Sit at the design-system layer. Block scattered components, hardcoded values, brand drift, and naming-by-appearance before they ship. Emit a scored audit, a refactor plan (when drifting), or a build-out plan (when broken).
Web medium first. Native (Swift, Compose), TUI, print, and email are candidates to become sibling skills when migration triggers fire — see TESTS.md.
Modes
Audit mode (default)
Trigger: "atomic audit", "brand audit", "/atomic-brand"
Behavior:
- Detect brand-token source via the failover chain
- Walk the component library (CSS, HTML, React/Vue/Svelte files)
- Apply the 8-dimension rubric per
references/audit-rubric.md - Emit the Atomic Brand Audit with findings
- Issue verdict; emit downstream artifact (refactor plan or build-out plan)
Refactor mode
Trigger: "find duplicate components", "consolidate components"
Behavior:
- Run audit
- Focus the refactor plan on the highest-leverage consolidations and renames
- Emit
refactor-plan.mdordered by leverage
Build-out mode
Trigger: automatic when verdict is broken
Behavior:
- Identify which tokens and patterns are missing
- Emit
build-out-plan.mdlisting required tokens, atoms, molecules, organisms - Sequence the build by T-shirt size (XS → XL) where applicable
The failover chain (brand detection)
Three sources of truth, tried in order:
| Step | Source | Confidence |
|---|---|---|
| 1 | Explicit token file (tokens.css, tailwind.config.{js,ts}, tokens.json, theme.ts) |
high |
| 2 | Brand asset image (logo, screenshot, style guide PDF) | medium |
| 3 | Scrape live URL — extract computed styles from rendered pages | low |
If step 1 finds a token file, use it. Skip 2 and 3.
If step 1 fails, try step 2.
If step 2 fails, try step 3.
If all three fail, verdict = broken; build-out plan starts with "no
brand tokens defined."
See references/failover-chain.md.
The 8 audit dimensions
| # | Dimension | What it scores |
|---|---|---|
| 1 | Token compliance | % of color/spacing/type values using tokens vs. hardcoded |
| 2 | Atomic discipline | Honest hierarchy: atoms compose into molecules compose into organisms |
| 3 | Naming integrity | Components named by role, not appearance |
| 4 | Brand coherence | Visual identity consistent across the surface |
| 5 | Scale discipline | Values come from defined scales (spacing, type, color) |
| 6 | Composition health | No cross-tree reaches; clean dependency graph |
| 7 | Duplication | Minimum number of components per job |
| 8 | Variant clarity | Variants are declared and named, not implicit |
What ships with it
22 files 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.
- .claude-plugin/plugin.json 532 B
- assets/audit-report-schema.json 3.1 KB
- assets/audit-template.md 3.0 KB
- fixtures/expected-audit.md 5.2 KB
- fixtures/input-component-library.md 6.3 KB
- fixtures/input-tokens.css 2.1 KB
- prompts/audit-brand-coherence.md 6.5 KB
- prompts/audit-component-library.md 6.8 KB
- prompts/audit-token-compliance.md 5.4 KB
- prompts/audit-url.md 5.4 KB
- prompts/build-out-plan.md 6.6 KB
- prompts/parse-image-for-brand.md 6.5 KB
- prompts/refactor-plan.md 6.4 KB
- prompts/scrape-for-brand.md 5.9 KB
- README.md 1.3 KB
- references/atomic-design.md 6.5 KB
- references/audit-rubric.md 5.6 KB
- references/brand-tokens.md 5.4 KB
- references/composition-rules.md 5.7 KB
- references/failover-chain.md 6.2 KB
- references/failure-modes.md 6.6 KB
- TESTS.md 5.9 KB
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.
- 10d ago First seen · 179 lines · 154 tokens per session scan A 013e0102ba83
atomic-brand is a skill published in the GitHub repository infolog-io/skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 154 tokens to every session and 1,642 once invoked, about $0.0008 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
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
better-colors
Helps you build a color system and answer anything about color in your project. You can generate palettes, use semantic tokens, convert between formats, check contrast and more.