tool-ui AGENTS.md

Project instructions for working on Tool UI, a Next.js documentation and component-library site inside a pnpm monorepo, which is a repository containing several related projects.

In plain words
What is it for?
Running the development server, checking code, testing, formatting, and understanding which API key and tools the project uses.
Why use it?
They give an assistant the project layout, required commands, services, and setup details so it can work without guessing.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/assistant-ui/tool-ui/agents-md
Clone the repo
git clone --depth 1 https://github.com/assistant-ui/tool-ui

Made for: Codex, OpenCode.

Per session 513 This file is loaded in full into every session.
When invoked 513 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00513 $0.00513
Opus 5 $0.00257 $0.00257
Sonnet 5 $0.00103 $0.00103
Haiku 4.5 $0.00051 $0.00051

Measured 2d ago against content hash b72df86e80ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tool-ui 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.

AGENTS.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Cursor Cloud specific instructions

Project overview

Tool UI is a Next.js 16 documentation/demo site and copy-paste component library for AI assistant interfaces. The app lives in apps/www/ within a pnpm monorepo. There is no database, no Docker, and no required background services beyond the Node.js dev server.

Running services

  • Dev server: pnpm dev (Turbopack, port 3000). The static docs, gallery, and component previews work without any API keys.
  • Chat/Playground features require OPENAI_API_KEY in .env (see .env.example). Without it the chat API routes return errors, but the rest of the site functions normally.

Commands reference

All standard commands are documented in CLAUDE.md. Key ones:

Task Command
Dev server pnpm dev
Lint + typecheck + format pnpm check
Tests (Vitest) pnpm test
Fix lint issues pnpm lint:fix
Typecheck only pnpm typecheck

Non-obvious caveats

  • Typecheck uses tsgo (@typescript/native-preview), not standard tsc. The pnpm typecheck command runs tsgo --noEmit.
  • Formatter is oxfmt, not Prettier. Run pnpm format to format or pnpm format:check to verify. It handles Tailwind class sorting and import sorting.
  • Linting is split: oxlint handles standard rules; eslint is retained only for no-restricted-syntax, no-restricted-imports, custom tool-ui/* rules, and React Compiler hooks. pnpm check runs both in parallel.
  • pnpm install triggers prepare which sets up git hooks via tsx apps/www/scripts/install-git-hooks.ts. The hooks directory is .githooks/.
  • Pre-existing lint warnings (60 warnings, 0 errors): these are known oxlint a11y warnings in the codebase and are not regressions.
  • Build uses --experimental-build-mode=compile: pnpm build runs next build --experimental-build-mode=compile.

Read the full file on GitHub · 34 lines

Changes

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.

  1. 2d ago First seen · 34 lines · 513 tokens per session scan A b72df86e80ec

Subscribe to this mod's changes

tool-ui AGENTS.md is an instructions file published in the GitHub repository assistant-ui/tool-ui (773 stars, last pushed 3mo ago), licensed MIT. It adds 513 tokens to every session, about $0.0026 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.