agentmods.dev

limps CLAUDE.md

limps CLAUDE.md is an instructions file for coding agents from paulbreuler/limps. It costs 1,941 tokens per session, scanned A, original, MIT.

Repository instructions for Claude Code, an AI coding assistant, covering a JavaScript monorepo with two related packages.

In plain words
What is it for?
Running commands across all packages or one package, starting development watch mode, and running a specific Vitest test.
Why use it?
They give the assistant the project structure and exact commands, reducing mistakes when building, testing, linting, or validating the code.

Instructions file

not rated 10 6mo ago A scan 1,941 tokens original MIT
View the source file paulbreuler/limps
Install

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.

agentmods
npx agentmods add instructions/paulbreuler/limps/claude-md
Clone the repo
git clone --depth 1 https://github.com/paulbreuler/limps

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.

agentmods badge for limps CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/paulbreuler/limps/claude-md.svg)](https://agentmods.dev/instructions/paulbreuler/limps/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/paulbreuler/limps/claude-md"><img src="https://agentmods.dev/badge/instructions/paulbreuler/limps/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,941 This file is loaded in full into every session.
When invoked 1,941 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.01941 $0.01941
Opus 5 $0.00971 $0.00971
Sonnet 5 $0.00388 $0.00388
Haiku 4.5 $0.00194 $0.00194

Measured 3d ago against content hash 1fdd87c1df6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

limps 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 3d 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 · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 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.

Monorepo Structure

This is an npm workspaces monorepo with two packages:

  • packages/limps - @sudosandwich/limps - The main MCP planning server
  • packages/limps-headless - @sudosandwich/limps-headless - Headless UI extension for limps

Build and Development Commands

# Root-level commands (run across all workspaces)
npm run build          # Compile TypeScript to dist/ in all packages
npm test               # Run all tests across workspaces
npm run lint           # ESLint check across workspaces
npm run validate       # Full validation: format + lint + type-check + build + test

# Single package commands
npm run build -w packages/limps           # Build only limps
npm run test -w packages/limps            # Test only limps
npm run build -w packages/limps-headless # Build only limps-headless

# Development
npm run dev -w packages/limps             # Watch mode for limps

Running a Single Test

cd packages/limps
npx vitest run tests/path/to/file.test.ts
npx vitest run -t "test name pattern"

Architecture Overview

limps is an MCP (Model Context Protocol) server for AI agent plan management. It provides tools and resources that AI assistants (Claude Desktop, Cursor, etc.) can use to manage planning documents and tasks.

Core Components (packages/limps)

Entry Points:

  • src/cli.tsx - Pastel-based CLI entry point (main user interface)
  • src/index.ts - Direct server invocation for backwards compatibility (stdio transport)
  • src/server-main.ts - Server initialization with config loading, database setup, and file watcher
  • src/server-http.ts - HTTP daemon server using StreamableHTTPServerTransport
  • src/commands/serve.tsx - stdio-to-HTTP bridge for Claude Desktop/Cursor (uses StreamableHTTPClientTransport)

MCP Layer:

  • src/server.ts - Creates MCP server instance with @modelcontextprotocol/sdk
  • src/tools/index.ts - Registers 14 MCP tools (document CRUD, plan management, task status)
  • src/resources/index.ts - Registers 4 MCP resources (plans://index, plans://summary/, plans://full/, decisions://log)

Read the full file on GitHub · 213 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.

  1. 3d ago First seen · 213 lines · 1,941 tokens per session scan A 1fdd87c1df6b

Subscribe to this mod's changes

limps CLAUDE.md is an instructions file published in the GitHub repository paulbreuler/limps (10 stars, last pushed 6mo ago), licensed MIT. It adds 1,941 tokens to every session, about $0.0097 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.

LLMai-agentsai-planningai-testing-best-practicesclicli-tool
Related

Other instructions, from other repositories

open-agent-hub AGENTS.md

AGENTS.md instructions for guanyang/open-agent-hub, covering agents.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.

guanyang/open-agent-hub · 485 tokens

gmgn-skills CLAUDE.md

Instructions for GMGNAI/gmgn-skills, covering claude.md, critical rule — read this first, project overview, available skills and quick decision guide.

GMGNAI/gmgn-skills · 2,591 tokens

map-framework CLAUDE.md

Instructions for azalio/map-framework, covering map framework (mapify-cli) — agent instructions, what this repo is, critical invariant: template single-source render, skill catalog invariant and how to work in this repo.

azalio/map-framework · 1,601 tokens

core copilot-instructions.md

Instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.

asdecided/core · 3,534 tokens

PromptHub AGENTS.md

AGENTS.md instructions for legeling/PromptHub, covering prompthub — project context & development rules, 0. agent operating contract, 0.1 source-of-truth lookup order, 0.2 mandatory change gate and 0.3 existing-feature modification rule.

legeling/PromptHub · 12,215 tokens

Atomic-Spec CLAUDE.md

Instructions for Chappygo-OS/Atomic-Spec, covering claude.md, what this repository is, architecture — the phase pipeline, critical conventions and common commands.

Chappygo-OS/Atomic-Spec · 3,322 tokens