What is agent-planner-mcp CLAUDE.md?

Project instructions for AgentPlanner's MCP server and command-line client. MCP, the Model Context Protocol, is a way for AI tools to connect to external services; this project also provides a local command-line program and a one-click Claude Desktop package.

Developing or validating AgentPlanner's Node.js MCP server, its local CLI, its HTTP or standard-input transports, its Claude Desktop bundle, and its agent-facing documentation.

They give agents the commands, documentation locations, and testing checks needed to work safely on the server. They also explain how the server can run through local, HTTP, or Claude Desktop setups.

How TAgents/agent-planner-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to TAgents/agent-planner-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/TAgents/agent-planner-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/TAgents/agent-planner-mcp

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tagents/agent-planner-mcp/claude-md.svg)](https://agentmods.dev/instructions/tagents/agent-planner-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/tagents/agent-planner-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tagents/agent-planner-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,417 This file is loaded in full into every session.

When invoked 1,417 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.01417	$0.01417
Opus 5	$0.00709	$0.00709
Sonnet 5	$0.00283	$0.00283
Haiku 4.5	$0.00142	$0.00142

Measured 8d ago against content hash d62c7f17686c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agent-planner-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 8d 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.

CLAUDE.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 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.

The repository root (../CLAUDE.md) describes the broader Talking Agents monorepo. This file is the MCP-server-specific guide.

What this is

agent-planner-mcp is the Model Context Protocol server for AgentPlanner, plus a thin local CLI (agent-planner-mcp <command>) for task-driven workflows. Node.js + @modelcontextprotocol/sdk + Express + axios. License MIT (more permissive than the backend/UI). Published to npm; also packaged as a .mcpb bundle for one-click Claude Desktop install.

Agent-facing documentation lives in SKILL.md (complete reference for LLMs) and AGENT_GUIDE.md (quick reference). Keep these in sync when tool shapes change.

Commands

npm start                       # stdio transport (for Claude Desktop / Code / Cursor)
npm run start:http              # HTTP/SSE transport on PORT (default 3100)
npm run dev                     # nodemon stdio
npm run dev:http                # nodemon HTTP
npm test                        # Jest
npm run validate:mcp-loop       # __tests__/agent-loop-facade.test.js (--runInBand)
node test-tools.js              # ad-hoc tool exerciser
npm run setup                   # interactive wizard (Claude Desktop)
npm run setup-claude-code       # interactive wizard (Claude Code)

# .mcpb bundle (Claude Desktop one-click install)
npm run build:mcpb              # install --omit=dev + pack → agent-planner.mcpb
npm run validate:mcpb           # schema-check manifest.json

Local CLI (thin client, not MCP)

npx agent-planner-mcp login --token <t> --api-url <url> [--plan-id <id>]
npx agent-planner-mcp tasks [--plan-id <id>]
npx agent-planner-mcp next [--plan-id <id>] [--fresh]
npx agent-planner-mcp context --plan-id <id> --node-id <id>
# … plus explicit writeback commands. README.md has the full loop.

Mental model: the AP API is the source of truth; .agentplanner/ files are a regeneratable cache the agent reads. Status changes are explicit writebacks — no live sync.

Read the full file on GitHub · 92 lines

Changes

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.

8d ago First seen · 92 lines · 1,417 tokens per session scan A d62c7f17686c

Subscribe to this mod's changes

agent-planner-mcp CLAUDE.md is an instructions file published in the GitHub repository TAgents/agent-planner-mcp (3 stars, last pushed 28d ago), licensed MIT. It adds 1,417 tokens to every session, about $0.0071 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.

Building agents

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

agent-planner-mcp: Instructions file for Claude Code