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/modelcontextprotocol/typescript-sdk/claude-mdgit clone --depth 1 https://github.com/modelcontextprotocol/typescript-sdkWhat 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 | $0.03530 | $0.03530 |
| Opus 5 | $0.01765 | $0.01765 |
| Sonnet 5 | $0.00706 | $0.00706 |
| Haiku 4.5 | $0.00353 | $0.00353 |
Grade A, and why
typescript-sdk CLAUDE.md scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- The package root entry must stay runtime-neutral so browser and Cloudflare Workers bundlers can consume it. Exports whose module graph transitively touches unpolyfillable Node builtins (`node:child_process`, `node:net` The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 285 lines · 3,530 tokens per session scan A c0752ffb9e92
typescript-sdk CLAUDE.md is an instructions file published in the GitHub repository modelcontextprotocol/typescript-sdk (13,281 stars, last pushed 2d ago), with no licence file. It adds 3,530 tokens to every session, about $0.0176 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
mcp-ts AGENTS.md
Instructions for zonlabs/mcp-ts, covering agents.md — mcp-ts monorepo, what is this?, repository structure, key architectural decisions and single-table session design.
fizzy-do-mcp AGENTS.md
Instructions for ryanyogan/fizzy-do-mcp, covering using vite+, the unified toolchain for the web, vite+ workflow, start, develop and execute.
vscode design-philosophy.instructions.md
VS Code design philosophy — the shared Values→Principles→Moves vocabulary for reasoning about UI in design terms rather than raw pixels. Use when creating, editing, or reviewing any visual surface (CSS, DOM, theming, icons, motion). Name the value/principle before reaching for a token.
deepagents AGENTS.md
Instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
mcp-dotnet-samples AGENTS.md
Instructions for microsoft/mcp-dotnet-samples, covering agents.md - mcp .net samples, project overview, project structure and architecture, repository organization and sample components.
walkerOS CLAUDE.md
Instructions for elbwalker/walkerOS, covering claude.md and important: use agent.md.