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/jasonhnd/design-md-generator/copilot-instructionsgit clone --depth 1 https://github.com/jasonhnd/design-md-generatorWrote 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/jasonhnd/design-md-generator/copilot-instructions)<a href="https://agentmods.dev/instructions/jasonhnd/design-md-generator/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/jasonhnd/design-md-generator/copilot-instructions.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 | $0.00460 | $0.00460 |
| Opus 5 | $0.00230 | $0.00230 |
| Sonnet 5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
design-md-generator copilot-instructions.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 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- design-md-generator AGENTS.md — 100% identical, 0 lines differ
- design-md-generator GEMINI.md — 100% identical, 0 lines differ
- design-md-generator CLAUDE.md — 100% identical, 0 lines differ
What it actually says
Design MD Generator
You have access to a design system extraction tool. When the user asks you to match a website's visual style, build UI that looks like a specific site, or create a DESIGN.md:
Run the full pipeline without stopping. Do not ask "should I proceed?" between steps.
Full Pipeline (one command flow)
# 1. Extract design tokens
cd /path/to/dmdg && npx ts-node scripts/extract.ts <URL>
# 2. [YOU] Read tokens.json + screenshots, write DESIGN.md following SKILL.md spec
# Write all 9 sections without pausing. Self-audit. Fix issues.
# 3. Validate
cd /path/to/dmdg && npx ts-node scripts/validate.ts output/<domain>/DESIGN.md output/<domain>/tokens.json
# 4. Generate report + proof
cd /path/to/dmdg && npx ts-node scripts/preview-gen.ts output/<domain>/tokens.json output/<domain>/
cd /path/to/dmdg && npx ts-node scripts/proof.ts <URL> output/<domain>/tokens.json output/<domain>/
cd /path/to/dmdg && npx ts-node scripts/report-gen.ts output/<domain>/tokens.json output/<domain>/ output/<domain>/DESIGN.md
# 5. Open report for user
open output/<domain>/report.html
Using an Existing DESIGN.md
If a DESIGN.md already exists in the project:
- Read it completely before writing any UI code
- Use ONLY the colors, fonts, sizes, and shadows specified in it
- Do NOT invent values not present in the document
- Follow Section 9 (Agent Prompt Guide) for quick reference
Critical Rules
- ALL numerical values MUST come from tokens.json — never hallucinate
- 6-digit lowercase hex (#ffffff, not #FFF)
- Numeric font weights (400, 700) not words (bold)
- Do not stop between steps to ask for confirmation
- Present only the final result
Full Specification
See SKILL.md for the complete 21-step workflow, format spec, writing style guide, and quality checklist.
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 First seen · 48 lines · 460 tokens per session scan A 66c061b571b7
design-md-generator copilot-instructions.md is an instructions file published in the GitHub repository jasonhnd/design-md-generator (10 stars, last pushed 4mo ago), licensed MIT. It adds 460 tokens to every session, about $0.0023 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
spectrum-design-data CLAUDE.md
Claude Code instructions for adobe/spectrum-design-data, covering spectrum tokens — claude code rules, tooling invariants, monorepo layout, changeset rules (ci-enforced) and copyright & license.
montology CLAUDE.md
Claude Code instructions for shinyobjectz/montology, covering montology — repo instructions, the shape and ground rules.
spectrum-design-data AGENTS.md
AGENTS.md instructions for adobe/spectrum-design-data, covering agent instructions, quick reference, rules, non-interactive shell commands and session completion.
design-md-extractor CLAUDE.md
Instructions for jpoindexter/design-md-extractor, covering claude.md, commands, run a single test file, cli usage (after build) and architecture.
Design-Learn CLAUDE.md
Instructions for GalaxyXieyu/Design-Learn, covering claude.md, todo, quick start, server and vscode extension.
google-fonts-skill CLAUDE.md
Claude Code instructions for sliday/google-fonts-skill, covering auto-google-font and python.