Diagram Design is a tool for creating editorial-style diagrams as self-contained HTML and SVG files, covering layouts such as flows, system architectures, Sankey diagrams, maps, and schemas. Designers and coding-agent users can use it to produce branded static diagrams or redraw Mermaid and draw.io sources. The catalogue commands, plugin, and skill provide the agent workflow for generating these diagrams.
Borrowing it
Nothing to install: this file belongs to cathrynlavery/diagram-design. 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/cathrynlavery/diagram-design/main/AGENTS.mdgit clone --depth 1 https://github.com/cathrynlavery/diagram-designWrote 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/cathrynlavery/diagram-design/agents-md)<a href="https://agentmods.dev/instructions/cathrynlavery/diagram-design/agents-md"><img src="https://agentmods.dev/badge/instructions/cathrynlavery/diagram-design/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/cathrynlavery/diagram-design/agents-md"><img src="https://agentmods.dev/badge/instructions/cathrynlavery/diagram-design/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 | $0.00643 | $0.00643 |
| Opus 5.5 | $0.00257 | $0.00257 |
| Sonnet 5.5 | $0.00129 | $0.00129 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
diagram-design 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 4d 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notes for coding agents
Read CONTRIBUTING.md before changing anything. It has the gate suite and the rules for each kind of change. This file covers the parts of adding a diagram that agents keep missing.
Adding a diagram type or variant
Follow "Adding a new diagram type" in CONTRIBUTING.md. The suite fails until these are done:
- Gallery. Register every example in
skills/diagram-design/assets/index.html. A new type gets the next number. Any other example of an existing type is a lettered variant: it goes directly after its parent withdata-parent-typeand a lettered eyebrow (28c). GitHub Pages publishesskills/diagram-design/assets/when the PR merges, so the live gallery needs no separate step. - Type count (new type). Raise
VISUAL_TYPE_COUNTinscripts/verify-docs-sync.pyandscripts/verify-semantic-motion.py, and the hardcoded count inscripts/verify-screenshot-freshness.pyandscripts/render-canonical-screenshots.py. Then fix every count the suite reports: the README, SKILL.md, CONTRIBUTING,onboarding.mdandsemantic-patterns.md, plus a new amendment in ADR 0002. - Plugin manifests. Keep
descriptionandkeywordsidentical across.claude-plugin,.codex-plugin,.factory-pluginand.qoder-plugin. A type whose selection-table name differs from the word used in the descriptions needs aDESCRIPTION_ALIASESentry inverify-docs-sync.py. Leaveversionalone; main bumps it after merge (ADR 0009).
Nothing checks these, so do them in the same PR:
- README thumbnail (new type). Run
scripts/render-canonical-screenshots.py, add the cell with its full-size PNG link to the grid under "What it makes", then runscripts/build-readme-thumbs.py; it only builds thumbnails for PNGs the README already links. Update "01 to N" in the gallery sentence below the grid. - README named variants. Line, Scatter and Treemap have named variants (slopegraph, bubble, marimekko and others). A new one goes in the "Several types have named variants" line.
- README file tree (new type). Add the new
type-*.mdto the tree under "Architecture", sorted by type name. - Layout budget (new type). Add the type's row to the complexity budget table in
skills/diagram-design/references/layout-budget.md.
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.
- 4d ago First seen · 25 lines · 643 tokens per session scan A 6a8dad531037
diagram-design AGENTS.md is an instructions file published in the GitHub repository cathrynlavery/diagram-design (61,060 stars, last pushed today), licensed MIT. It adds 643 tokens to every session, about $0.0026 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 2026-10-22.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.