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/joho/pocketsmith-mcp/claude-mdgit clone --depth 1 https://github.com/joho/pocketsmith-mcpWrote 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/joho/pocketsmith-mcp/claude-md)<a href="https://agentmods.dev/instructions/joho/pocketsmith-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/joho/pocketsmith-mcp/claude-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 | $0.03269 | $0.03269 |
| Opus 5 | $0.01635 | $0.01635 |
| Sonnet 5 | $0.00654 | $0.00654 |
| Haiku 4.5 | $0.00327 | $0.00327 |
Grade A, and why
pocketsmith-mcp CLAUDE.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 4d 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 — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is a production-ready TypeScript template for building Model Context Protocol (MCP) servers and clients following the MCP 2025-03-26 specification. It provides a comprehensive foundation with built-in utilities, authentication, error handling, and service integrations.
Key Stats:
- 57 TypeScript source files
- 32 directories in src/
- Supports both stdio and HTTP (SSE) transports
- Built-in authentication (JWT/OAuth)
- Comprehensive error handling and logging
- Ready-to-use DuckDB and OpenRouter integrations
Development Commands
Build & Run
npm run build- Build TypeScript and make executablenpm run rebuild- Clean build (removes node_modules, logs, dist)npm start- Run the built server (stdio transport)npm run start:stdio- Run server with stdio transport and debug loggingnpm run start:http- Run server with HTTP transport and debug logging
Development Tools
npm run format- Format code with Prettiernpm run docs:generate- Generate TypeDoc documentationnpm run tree- Generate project structure treenpm run inspector- Launch MCP inspector for debuggingnpm run depcheck- Check for unused dependenciesnpm run fetch-spec- Fetch OpenAPI specificationnpm run db:duckdb-example- Run DuckDB example with debug logging
Testing & Quality
Important: No specific test framework is configured. Before adding tests:
- Check README or search codebase for testing approach
- Ask user for preferred test framework if not found
- Always run linting after code changes
Project Architecture
Core Components
Entry Point (src/index.ts):
- Main application entry with graceful shutdown handling
- Initializes logger and configuration
- Starts appropriate transport (stdio/HTTP)
- Handles process signals and unhandled errors
Configuration (src/config/index.ts):
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.
- 4d ago First seen · 429 lines · 3,269 tokens per session scan A d7deadeb34bd
pocketsmith-mcp CLAUDE.md is an instructions file published in the GitHub repository joho/pocketsmith-mcp (11 stars, last pushed 1y ago), licensed Apache-2.0. It adds 3,269 tokens to every session, about $0.0163 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
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.