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/abboskhonov/tasteui/agents-mdgit clone --depth 1 https://github.com/abboskhonov/tasteuiWrote 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/abboskhonov/tasteui/agents-md)<a href="https://agentmods.dev/instructions/abboskhonov/tasteui/agents-md"><img src="https://agentmods.dev/badge/instructions/abboskhonov/tasteui/agents-md.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 5.1 | $0.01458 | $0.01458 |
| Opus 5 | $0.00729 | $0.00729 |
| Sonnet 5 | $0.00292 | $0.00292 |
| Haiku 4.5 | $0.00146 | $0.00146 |
Grade A, and why
tasteui 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 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.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions for tokenui
This repository is a monorepo with a TanStack Start frontend and a Hono API backend. These notes are for agentic coding work in this repo and should be kept current.
Repo Layout
apps/web/ # TanStack Start frontend (port 3000)
src/
routes/ # File-based TanStack Router routes
components/ # React components
ui/ # shadcn/ui components
features/ # Feature-based modules
lib/ # Utilities, API clients, queries
hooks/ # Custom React hooks
styles.css # Tailwind + global styles
apps/api/ # Hono API backend (port 3001)
src/
app.ts # Hono app with routes
index.ts # Server entry
auth/ # Better Auth configuration
db/ # Drizzle ORM schema and connection
storage/ # R2 storage utilities
drizzle/ # Database migrations
Build And Run
# Frontend
cd apps/web && bun run dev # Vite dev server on port 3000
cd apps/web && bun run build # Production build
cd apps/web && bun run preview # Preview built app
# API
cd apps/api && bun run dev # Hono dev server on port 3001
cd apps/api && bun run deploy # Cloudflare Workers deploy
# Database
cd apps/api && bun run db:generate # Generate Drizzle migrations
cd apps/api && bun run db:migrate # Apply migrations
cd apps/api && bun run db:push # Push schema changes directly
cd apps/api && bun run db:studio # Open Drizzle Studio
cd apps/api && bun run db:backfill # Run data backfill script
Lint, Format, Typecheck
cd apps/web && bun run lint # ESLint
cd apps/web && bun run format # Prettier write mode
cd apps/web && bun run typecheck # TypeScript no-emit check
Testing
The active test runner is Vitest in apps/web.
cd apps/web && bun run test # Run all tests once
cd apps/web && bun run test -- path/to.test.tsx # Run a single test file
cd apps/web && bun run test -- -t "name" # Run tests matching a name
cd apps/web && bun run test -- path/to.test.tsx:42 # Run the test at a line
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 · 156 lines · 1,458 tokens per session scan A 6049d0cb9ec6
tasteui AGENTS.md is an instructions file published in the GitHub repository abboskhonov/tasteui (24 stars, last pushed 1mo ago), licensed MIT. It adds 1,458 tokens to every session, about $0.0073 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
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.
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).
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.
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.
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).