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/astroblocksmod/scratchmcp/agents-mdgit clone --depth 1 https://github.com/AstroBlocksMod/ScratchMCPWhat 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 | $0.00548 | $0.00548 |
| Opus 5 | $0.00274 | $0.00274 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
ScratchMCP 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.
What it actually says
AGENTS.md
You are an expert in JavaScript, Vite, Rolldown, tsdown, and library development. You write maintainable, performant, and accessible code.
Layout
scratch-mcp — the MCP server — is the repo root: its sources are in
src/, its tests in test/, and it is published from the root package.json.
The libraries it builds on are workspace packages:
packages/scratch4js— the.sb3format library (published)packages/s-api4js— the scratch.mit.edu API wrapper (published)packages/userscript— the TurboWarp Desktop userscript (private)
Commands
The toolchain is Vite+ (vp), which bundles Vite,
Rolldown, tsdown, Oxlint and Oxfmt behind one binary.
pnpm run build— build every workspace package (vp run -r build)pnpm run dev— watch mode across packagespnpm test— the MCP server'snode --testsuitepnpm run lint— Oxlint (vp lint)pnpm run fmt— Oxfmt (vp fmt)pnpm run check— format, lint and type checks in one pass (vp check)pnpm run docs:dev/docs:build— the VitePress site indocs/pnpm run mcpb— build the.mcpbbundlescripts/bump-version.sh <version>— bump every hard-coded version at once
Conventions
- Lint and format config live in the root
vite.config.ts(lint/fmtblocks), not in.oxlintrc.jsonor.oxfmtrc.json— Vite+ keeps it in one place. Format is single quotes at 80 columns. - The libraries are plain JavaScript with JSDoc types.
vp packbuilds the JS;tscemits the.d.tsfiles (the bundled-dts path cannot follow JSDoc types through.jsre-exports). - Run
pnpm run lintandpnpm run fmtbefore committing.
Docs
- Vite+: https://viteplus.dev/
- tsdown: https://tsdown.dev/
- Oxc (Oxlint / Oxfmt): https://oxc.rs/
- VitePress: https://vitepress.dev/
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 · 47 lines · 548 tokens per session scan A 1e46d0cb0e5f
ScratchMCP AGENTS.md is an instructions file published in the GitHub repository AstroBlocksMod/ScratchMCP (0 stars, last pushed 7d ago), licensed MPL-2.0. It adds 548 tokens to every session, about $0.0027 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
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.
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.