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/luko248/css-first/agents-mdgit clone --depth 1 https://github.com/Luko248/css-firstWhat 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 | $0.00611 | $0.00611 |
| Opus 5 | $0.00305 | $0.00305 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
css-first 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 yesterday.
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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure (Bun Monorepo)
mcp-css-first/
├── packages/
│ ├── core/ # @css-first/core - shared CSS services
│ │ └── src/ # MDN client, suggestions, features, types
│ ├── cli/ # @depthark/css-first - npm package (stdio/HTTP)
│ │ └── src/ # MCP server entrypoint
│ └── worker/ # @css-first/worker - Cloudflare Workers (SSE)
│ └── src/ # McpAgent class for remote MCP
├── wrangler.toml # Cloudflare Workers deployment config
└── smithery.yaml # Smithery registry config
Build, Test, and Development Commands
bun install # Install all dependencies
bun run build # Build all packages
bun run build:core # Build @css-first/core only
bun run build:cli # Build @depthark/css-first only
bun run typecheck # Type check all packages
bun run lint # Run ESLint
bun run deploy:worker # Deploy to Cloudflare Workers
bun run publish:cli # Publish CLI to npm
Package-specific commands (run from package directory)
packages/cli:bun run build- bundles with@vercel/nccpackages/core:bun run build- compiles TypeScriptpackages/worker:bun run dev- local Cloudflare development
Coding Style & Naming Conventions
- TypeScript with strict mode enabled
- Indentation is 2 spaces; prefer double quotes
- Use
camelCasefor variables/functions,PascalCasefor types/classes - Follow ESLint rules (unused args prefixed with
_)
Package Dependencies
@css-first/coreis internal (private: true), shared between cli and worker@depthark/css-firstis publishable to npm@css-first/workeris private, deployed to Cloudflare only
Testing Guidelines
- No automated test runner configured
- Rely on
bun run typecheckand manual CLI testing - Test worker locally with
cd packages/worker && bun run dev
Commit & Pull Request Guidelines
- Conventional Commits style:
feat:,fix:,chore:,docs:,refactor: - Keep commits scoped to single changes
- PRs should pass: build, lint, typecheck
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.
- yesterday First seen · 61 lines · 611 tokens per session scan A 6552dd697c09
css-first AGENTS.md is an instructions file published in the GitHub repository Luko248/css-first (4 stars, last pushed 6mo ago), licensed MIT. It adds 611 tokens to every session, about $0.0031 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
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.