claude-pip

claude-pip is a plugin for Claude Code from infolog-io/skills. Its manifest loads nothing; the 1 skill it bundles cost 256 tokens per session together, scanned A, original, MIT.

A Claude plugin for recording, reviewing, removing, and promoting rules about how Claude should work in a project.

In plain words
What is it for?
Use it to add project-wide or directory-specific rules, audit them, delete them by identifier or keyword, and move stable rules into standard project or user instruction files.
Why use it?
It preserves lessons from repeated mistakes or missed practices, such as planning or test-driven development (writing tests before implementation). It also helps remove rules that are no longer useful.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest. Also seen: mentions CLAUDE.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.

Claude Code
/plugin marketplace add infolog-io/skills
agentmods
npx agentmods add plugins/infolog-io/skills/claude-pip
Clone the repo
git clone --depth 1 https://github.com/infolog-io/skills

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 claude-pip

README.md
[![agentmods](https://agentmods.dev/badge/plugins/infolog-io/skills/claude-pip.svg)](https://agentmods.dev/plugins/infolog-io/skills/claude-pip)
Your own site
<a href="https://agentmods.dev/plugins/infolog-io/skills/claude-pip"><img src="https://agentmods.dev/badge/plugins/infolog-io/skills/claude-pip.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill cost 256 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

claude-pip 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 6d 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.

skills/claude-pip/.claude-plugin/plugin.json · 9 lines

What it actually says

{
  "name": "claude-pip",
  "version": "0.4.0",
  "description": "Performance Improvement Plan for Claude. Five triggers covering a rule's full lifecycle. CLAUDE PIP / LOCAL PIP capture rules (master or directory-scoped). OFF THE PIP removes by id or keyword. PRUNE THE PIP audits the rules; default verdict is keep (carry-forward is the point). PROMOTE THE PIP graduates stable rules to canonical homes (CLAUDE.md, DESIGN.md, user-global) — the user picks which. Every rule wrapped in HTML-comment markers so it can be removed mechanically.",
  "author": {
    "name": "Information Logistics",
    "url": "https://github.com/infolog-io"
  }
}
Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 256 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 6d ago First seen · 9 lines scan A 1346aa055d27

Subscribe to this mod's changes

claude-pip is a plugin published in the GitHub repository infolog-io/skills (4 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.