002_agent_cleanup

002_agent_cleanup is an agent for Claude Code from paulbreuler/limps. It costs 0 tokens per session (851 once invoked), scanned A, original, MIT.

A work assignment for removing an obsolete server command and updating the command-line package after replacement start and stop commands are ready.

In plain words
What is it for?
Use it to delete the old command, modify the CLI, update package dependencies and versioning, and coordinate against other agents' work.
Why use it?
It gives an agent a defined cleanup scope, dependencies, files, and completion status within a larger development plan.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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 agents/paulbreuler/limps/002_agent_cleanup
Clone the repo
git clone --depth 1 https://github.com/paulbreuler/limps

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.

agentmods badge for 002_agent_cleanup

README.md
[![agentmods](https://agentmods.dev/badge/agents/paulbreuler/limps/002_agent_cleanup.svg)](https://agentmods.dev/agents/paulbreuler/limps/002_agent_cleanup)
Your own site
<a href="https://agentmods.dev/agents/paulbreuler/limps/002_agent_cleanup"><img src="https://agentmods.dev/badge/agents/paulbreuler/limps/002_agent_cleanup.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 851 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00000 $0.00851
Opus 5 $0.00000 $0.00426
Sonnet 5 $0.00000 $0.00170
Haiku 4.5 $0.00000 $0.00085

Measured 2d ago against content hash ccea9cce39ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

002_agent_cleanup 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 2d 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.

plans/Completed/0049-persistent-http-server/agents/002_agent_cleanup.agent.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent 2: Cleanup — Remove serve, bump v3

Plan Location: plans/0049-persistent-http-server/0049-persistent-http-server-plan.md

Scope

Features: #6 Own: src/commands/serve.tsx (delete), src/cli.tsx, package.json Depend on: Agent 0 + Agent 1 (start/stop must work before removing serve) Block: Nothing

Interfaces

Receive (from Agent 0, Agent 1) ✅ READY when both are PASS

// Agent 1 provides working start/stop commands
// src/commands/start.tsx — replaces serve
// src/commands/stop.tsx — new

Features

#6: Remove limps serve and update CLI

TL;DR: Delete serve command, remove CLI bypass hack, bump to v3, add express dep. Status: GAP Files: src/commands/serve.tsx (delete), src/cli.tsx (modify), package.json (modify)

Steps:

  1. Delete src/commands/serve.tsx
  2. Modify src/cli.tsx — remove the serve bypass block (lines ~8-22 that detect serve in process.argv and call startMcpServer() directly bypassing Pastel). The start command doesn't need this hack because it uses HTTP transport, not stdio.
  3. Modify packages/limps/package.json:
    • "version": "3.0.0"
    • Add "express": "^5.0.1" to dependencies
    • Add "@types/express": "^5" to devDependencies
  4. Update any references to serve in help text, descriptions, or other commands (e.g., config command mentions serve)
  5. Check src/index.ts — if it calls startMcpServer() for backward compat, update or remove

TDD:

  1. serve is not a valid command → run limps serve → assert error or helpful message pointing to limps start
  2. start appears in help output → run limps --help → assert start and stop listed
  3. build succeeds without servenpm run build → assert clean compilation

Gotchas:

  • src/index.ts is a backward-compat entry for "bin" — may need updating to launch HTTP server instead of stdio
  • Check src/cli/config-cmd.ts for serve references in help text
  • Removing serve may break existing MCP client configs — this is intentional (v3 breaking change)

Read the full file on GitHub · 107 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. 2d ago First seen · 107 lines · 0 tokens per session scan A ccea9cce39ad

Subscribe to this mod's changes

002_agent_cleanup is an agent published in the GitHub repository paulbreuler/limps (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 851 tokens. 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 2026-09-03.