adobe/spectrum-design-data is a monorepo containing the design tokens, component schemas, specifications, and related datasets that define Adobe's Spectrum design system; a monorepo keeps these related packages in one repository. It is for Adobe Spectrum SDK and tooling developers who need canonical design-system data and validation artifacts. The catalogue add-ons provide workflows and integrations for working with this design data.
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 agentmods add instructions/adobe/spectrum-design-data/claude-mdgit clone --depth 1 https://github.com/adobe/spectrum-design-dataWrote 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/adobe/spectrum-design-data/claude-md)<a href="https://agentmods.dev/instructions/adobe/spectrum-design-data/claude-md"><img src="https://agentmods.dev/badge/instructions/adobe/spectrum-design-data/claude-md.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 | $0.01962 | $0.01962 |
| Opus 5 | $0.00981 | $0.00981 |
| Sonnet 5 | $0.00392 | $0.00392 |
| Haiku 4.5 | $0.00196 | $0.00196 |
Grade A, and why
spectrum-design-data 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 yesterday.
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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spectrum Tokens — Claude Code Rules
Tooling Invariants
- [email protected] — never use npm or yarn; use
pnpmfor installs and scripts - moon —
moon run <task>for all defined tasks;moon query projectsto survey the graph - AVA — all JS/TS tests (
test/**/*.test.js); each package has its ownava.config.js - changesets —
pnpm changesetfor every user-facing version bump; never edit versions manually - commitlint — conventional commits enforced; format:
type(scope): description- Types:
featfixdocsstylerefactortestchore - Breaking: append
!or addBREAKING CHANGE:footer
- Types:
- Node.js ~20.12 · ESM throughout (
"type": "module")
Monorepo Layout
packages/ — core libraries (tokens, design-data, design-data-spec, component-schemas, …)
tools/ — internal dev tooling (~20 packages)
docs/ — documentation sites and explorers
sdk/ — Rust workspace (crates: core, cli, tui, wasm)
Per-package build commands, test commands, and layout details live in each package's own
CLAUDE.md — they load on demand, not at session start.
Changeset Rules (CI-enforced)
- Bump level:
patch= bug fix;minor= additive or validation-behavior change;major= breaking - Body ≤ 20 lines (CI linter enforces). Verify before committing:
node tools/changeset-linter/src/cli.js check --fail-on-warnings - One intro sentence + one bullet per changed artifact. Rationale → PR description, not changeset.
- Format:
Short summary (closes #NNN). - **path/to/file**: what changed and why it matters.
Copyright & License
Every new file gets: Copyright YYYY Adobe. All rights reserved. with the current year.
Comment style matches language: // (Rust/JS/TS), # (YAML/moon.yml), block comment (C-style).
License: Apache-2.0.
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.
- yesterday First seen · 133 lines · 1,962 tokens per session scan A 3096c49f9500
spectrum-design-data CLAUDE.md is an instructions file published in the GitHub repository adobe/spectrum-design-data (151 stars, last pushed today), licensed Apache-2.0. It adds 1,962 tokens to every session, about $0.0098 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 2026-09-03.
Other instructions, from other repositories
daisyui code_generation_with_git.instructions.md
Instructions for saadeghi/daisyui, covering activation, initial setup, development loop, error handling and session end.
agentistics AGENTS.md
AGENTS.md instructions for blpsoares/agentistics, covering before starting implementation work, opening a pr, merging: squash a feature, merge a release, documentation and scope discipline.
event-store-adapter-js AGENTS.md
AGENTS.md instructions for j5ik2o/event-store-adapter-js, covering agents.md, 言語, github pull request のモニタリング, $grill-me 実行時の作業判断 and 軽い作業の場合.
Design-Learn CLAUDE.md
Instructions for GalaxyXieyu/Design-Learn, covering claude.md, todo, quick start, server and vscode extension.
design-pipeline CLAUDE.md
Claude Code instructions for 2233admin/design-pipeline, a project described as: 给 AI Agent 的前端设计管线：先写 DESIGN.md 与 MOTION.md，经 job 分发、OpenSpec 与证据门禁再写代码。.
Standby.Design CLAUDE.md
Claude Code instructions for KarstenKreh/Standby.Design, covering claude.md, npm publish (standby-design-mcp), deploys (website + remote mcp server) and pitfalls.