Borrowing it
Nothing to install: this file belongs to darkyzhou/carbon-design-guidelines. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/darkyzhou/carbon-design-guidelines/main/CLAUDE.mdgit clone --depth 1 https://github.com/darkyzhou/carbon-design-guidelinesWrote 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/instructions/darkyzhou/carbon-design-guidelines/claude-md)<a href="https://agentmods.dev/instructions/darkyzhou/carbon-design-guidelines/claude-md"><img src="https://agentmods.dev/badge/instructions/darkyzhou/carbon-design-guidelines/claude-md/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/instructions/darkyzhou/carbon-design-guidelines/claude-md"><img src="https://agentmods.dev/badge/instructions/darkyzhou/carbon-design-guidelines/claude-md.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 | $0.10887 | $0.10887 |
| Opus 5 | $0.05444 | $0.05444 |
| Sonnet 5 | $0.02177 | $0.02177 |
| Haiku 4.5 | $0.01089 | $0.01089 |
Grade A, and why
carbon-design-guidelines CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 480 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Carbon Design Guidelines
An agent-optimized Skill that teaches AI coding agents how to use IBM's Carbon Design System (v11) to write React UIs. The Skill output lives under skills/carbon-design-guidelines/; everything else in this repo is maintainer tooling.
Current design (unified components/ layout)
Earlier iterations split reference (props, tokens) and guide (design judgment) into two top-level trees. That split made cross-reading painful — an agent writing code for Modal had to juggle two files instead of one. The current layout unifies both under a single per-component folder and uses progressive disclosure via a tag protocol:
components/<Name>/index.md— the landing page; mirrors the source MDX outline; teaches decisions + constraints inline for anything that fits in ≤ 5 bullets, defers everything else to tagged regions in sibling files. Includes a## Propssection pointing to@carbon/reactsource files for prop definitions.components/<Name>/{formatting,content,variants,modifiers,accessibility}.md— sub-sections wrapped in<PascalCaseTag>...</PascalCaseTag>markers so the agent can Grep a single region.components/<Name>/images/— only images actually referenced in the folder.
## When to use / ## When not to use content is relocated OUT of per-component index.md files and UP to the root SKILL.md routing section — the agent needs decision guidance before opening any component folder.
Project structure
skills/carbon-design-guidelines/ # The skill (what agents consume)
SKILL.md # Passive-context index; routing + file conventions
components/<Name>/ # 41 component folders (one per @carbon/react component with website design docs)
index.md
formatting.md / content.md / variants.md / modifiers.md / accessibility.md
images/
foundations/<name>/ # 12 foundation docs (grid, color, spacing, typography, themes, motion, icons, pictograms, accessibility, content, carbon-for-ai, decisions)
index.md (+ sub-files + images/ where needed)
patterns/<name>/ # 17 design pattern docs (forms, dialog, notification, loading, empty-states, etc.)
index.md (+ sub-files + images/ where needed)
data-visualization/ # 8 data-viz docs for @carbon/charts-react
index.md # Entry point: installation, chart type selection, chart anatomy
color-palettes.md / axes-and-labels.md / legends.md / dashboards.md
spatial-charts.md / flow-charts.md / gantt-charts.md
images/
scripts/
carbon-assets-search.mjs # Bundled asset CLI (rebuild with `bun run build:assets`)
scripts/ # Maintainer dev tooling (not shipped with the skill)
generate-icons-index.ts # vendor/carbon/.../icons.yml → scripts/carbon-icons.json
generate-pictograms-index.ts # vendor/carbon/.../pictograms.yml → scripts/carbon-pictograms.json
generate-versions.ts # vendor/carbon/packages/*/package.json → skills/.../references/versions.md
carbon-assets-search.ts # CLI source bundled to skills/.../scripts/carbon-assets-search.mjs
carbon-icons.json / carbon-pictograms.json # Generated indexes (gitignored)
review-skill-docs.sh # Batched reviewer using `claude -p`
tests/
carbon-assets-search.test.ts # Vitest — exit codes + stdout/stderr snapshots
__snapshots__/
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 · 480 lines · 10,887 tokens per session scan A d26a60fb8028
carbon-design-guidelines CLAUDE.md is an instructions file published in the GitHub repository darkyzhou/carbon-design-guidelines (5 stars, last pushed 4mo ago), licensed MIT. It adds 10,887 tokens to every session, about $0.0544 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.