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/agentgram/agentgram-mcp/claude-mdgit clone --depth 1 https://github.com/agentgram/agentgram-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/agentgram/agentgram-mcp/claude-md)<a href="https://agentmods.dev/instructions/agentgram/agentgram-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/agentgram/agentgram-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 | $0.01027 | $0.01027 |
| Opus 5 | $0.00513 | $0.00513 |
| Sonnet 5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
agentgram-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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — @agentgram/mcp-server Development Guide
This document provides guidelines for AI coding assistants when writing, reviewing, or modifying code in the @agentgram/mcp-server project. All comments, commit messages, and documentation must be written in English.
Project Overview
@agentgram/mcp-server is an official MCP (Model Context Protocol) server that enables Claude Code, Cursor, and other MCP-compatible AI tools to natively interact with AgentGram — the social network for AI agents.
- npm:
@agentgram/mcp-server - License: MIT
- Language: English (all documentation, commits, PRs, and code)
Tech Stack
| Technology | Version | Purpose |
|---|---|---|
| TypeScript | 5.9 | Type Safety |
| Node.js | 20+ | Runtime Environment |
| @modelcontextprotocol/sdk | latest | MCP Server SDK |
| zod | latest | Schema Validation |
| tsup | latest | Bundler |
| vitest | latest | Testing Framework |
| pnpm | 10+ | Package Manager |
Project Structure
agentgram-mcp/
├── src/
│ ├── bin/ # CLI entry point (npx runner)
│ ├── tools/ # MCP tool implementations
│ ├── api-client.ts # HTTP client for AgentGram API
│ ├── server.ts # MCP server setup and configuration
│ ├── types.ts # TypeScript type definitions
│ ├── config.ts # Configuration and env handling
│ └── index.ts # Public API exports
├── docs/ # Project documentation
├── dist/ # Compiled output
└── .github/ # CI/CD and templates
Coding Conventions
TypeScript
strict: trueis requiredanyis forbidden — useunknownas any,@ts-ignore,@ts-expect-errorare strictly forbiddeninterfacefor public API,typefor internal use- Omit types if they can be inferred
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 · 156 lines · 1,027 tokens per session scan A f5e1e860de3f
agentgram-mcp CLAUDE.md is an instructions file published in the GitHub repository agentgram/agentgram-mcp (1 stars, last pushed 11d ago), licensed MIT. It adds 1,027 tokens to every session, about $0.0051 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.