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/manalkaff/opendesign/agents-mdgit clone --depth 1 https://github.com/manalkaff/opendesignWhat 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 | $0.00774 | $0.00774 |
| Opus 5 | $0.00387 | $0.00387 |
| Sonnet 5 | $0.00155 | $0.00155 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
opendesign 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 2d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions for this repository
This repo is OpenDesign — an open-source, skills-based version of Claude Design (the web design mode on claude.ai), packaged as a Claude Code plugin. When working inside this repository, your job is to maintain and extend those skills — not to run them.
Repo layout
skills/<skill-name>/SKILL.md— one folder per skill. EachSKILL.mdhas YAML frontmatter (name,description) followed by the skill body..claude-plugin/plugin.json— Claude Code plugin metadata..claude-plugin/marketplace.json— Claude Code marketplace entry. Skills are discovered by convention from./skills/; do not add askills[]field (Claude Code's schema rejects it)..cursor-plugin/plugin.json— Cursor plugin metadata..codex-plugin/plugin.json— Codex plugin metadata (richerinterfaceblock for app UI)..opencode/plugins/opendesign.js— OpenCode plugin (registers skills dir + injectsopendesignbootstrap into the first user message)..opencode/INSTALL.md— user-facing install notes for OpenCode.gemini-extension.json+GEMINI.md— Gemini CLI extension.GEMINI.md@-imports theopendesignskill as context.package.json— required so OpenCode can install the repo viagit+https://....mainpoints at the OpenCode plugin entry.README.md— user-facing. The "Available skills" table must match the actual skills shipped.
Rules when editing skills
- Skills are written in direct imperative voice. No marketing language, no apologies, no emoji.
- Every
SKILL.mdmust start with frontmatter containingnameanddescription.descriptionis a "Use when..." sentence that describes triggering conditions, not a summary of what the skill does. - Keep
opendesign/SKILL.mdas the entry-point/base skill. Specialist skills (wireframe,make-a-deck, etc.) are loaded on demand by the workflow described there. - If you add a new skill: create
skills/<name>/SKILL.mdwith frontmatter and add a row to the README table. Do not add a per-skill list to.claude-plugin/marketplace.json; Claude Code discovers skills from./skills/. - If you rename or remove a skill: update the README table and any direct references to that skill in the same change.
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.
- 2d ago First seen · 38 lines · 774 tokens per session scan A 46af51a20687
opendesign AGENTS.md is an instructions file published in the GitHub repository manalkaff/opendesign (255 stars, last pushed 2mo ago), licensed MIT. It adds 774 tokens to every session, about $0.0039 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 2026-08-30.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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).
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.
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 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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.