Vercel Labs' DS Skill Extraction Workshop is a starter repository for a workshop that teaches developers to turn a design system into reusable agent skills and use one to generate a Primer React interface. It guides participants through setup, generation, and visual review of the resulting application. The catalogue entries provide the skills and instructions used in the workshop.
Borrowing it
Nothing to install: this file belongs to vercel-labs/ds-skill-extraction-workshop. 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/vercel-labs/ds-skill-extraction-workshop/main/AGENTS.mdgit clone --depth 1 https://github.com/vercel-labs/ds-skill-extraction-workshopWrote 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/vercel-labs/ds-skill-extraction-workshop/agents-md)<a href="https://agentmods.dev/instructions/vercel-labs/ds-skill-extraction-workshop/agents-md"><img src="https://agentmods.dev/badge/instructions/vercel-labs/ds-skill-extraction-workshop/agents-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/vercel-labs/ds-skill-extraction-workshop/agents-md"><img src="https://agentmods.dev/badge/instructions/vercel-labs/ds-skill-extraction-workshop/agents-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 | $0.00534 | $0.00534 |
| Opus 5.5 | $0.00214 | $0.00214 |
| Sonnet 5.5 | $0.00107 | $0.00107 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
ds-skill-extraction-workshop AGENTS.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 2mo 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
Dry-runs use their own worktree
Before producing snapshot artefacts (/extract-ds-skill, a PRD build /primer-react implement prompts/*.md, prompts/issues.md, prompts/audit.md, anything frozen under dry-runs/): run git worktree list. Outputs go in the matching .claude/worktrees/dryrun-NN-<label>-iN/ (branch dryrun/NN-<label>-iN) — never a durable branch.
Each worktree gets its own node_modules — after creating it, run pnpm install --frozen-lockfile inside the worktree once. Never symlink node_modules to root. A shared node_modules isn't isolation: a single pnpm install in any one worktree rewrites root's top-level links to point into that worktree (we've watched root's next/react/react-dom get redirected into a sibling dryrun), and then git worktree remove-ing that worktree dangles the links and breaks the build for root and every worktree at once. pnpm hardlinks from the global store (~/Library/pnpm/store), so a per-worktree install is fast and costs almost no disk. package.json / pnpm-lock.yaml / pnpm-workspace.yaml are git-tracked, so the install is self-contained — Turbopack infers the worktree as its own root and has no symlink to distrust.
Where a change goes
- Dry-run-specific → dryrun branch:
dry-runs/<date>-<label>/snapshots (app files +harvest-log.md), generatedapp/artefacts, a freshly-extracted.claude/skills/<slug>/not yet promoted. - Durable → feature branch → PR →
main:.claude/skills/extract-ds-skill/, the promoted reference skill.claude/skills/primer-react/(lives on main; repaired via PR; copied read-only into worktrees as skill-under-test),dry-runs/TEMPLATE.md/README.md/SUMMARY.md, this file.
A freshly-extracted skill is dry-run-specific until promoted to main; after that, durable.
Unsure? Ask before writing — re-splitting commits later is worse.
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.
- 2mo ago First seen · 17 lines · 534 tokens per session scan A 5dc44da4a02e
ds-skill-extraction-workshop AGENTS.md is an instructions file published in the GitHub repository vercel-labs/ds-skill-extraction-workshop (13 stars, last pushed 4mo ago), licensed MIT. It adds 534 tokens to every session, about $0.0021 per session on Opus 5.5. 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 2026-08-30.
ds-skill-extraction-workshop AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ds-skill-extraction-workshop AGENTS.mdvercel-labs/ds-skill-extraction-workshop | Instructions file | 13 | 4mo ago | MIT | A | 534 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |