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/willywg/prp-manager/claude-mdgit clone --depth 1 https://github.com/willywg/prp-managerWrote 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/willywg/prp-manager/claude-md)<a href="https://agentmods.dev/instructions/willywg/prp-manager/claude-md"><img src="https://agentmods.dev/badge/instructions/willywg/prp-manager/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 5.1 | $0.00563 | $0.00563 |
| Opus 5 | $0.00282 | $0.00282 |
| Sonnet 5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
prp-manager 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 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.
How it starts
The opening of the file, as written. The whole thing — 49 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.
Project Overview
PRP Manager is an Agent Skill for creating and executing PRPs (Product Requirements Prompts) using Context Engineering principles. It enables AI agents to implement features with comprehensive context for one-pass implementation success.
This is an Agent Skill, not a traditional codebase with source code. It consists of markdown files that define skill behavior.
Repository Structure
prp-manager/ # Repository root (development files)
├── README.md # Installation and usage documentation
├── LICENSE # MIT License
├── CLAUDE.md # This file
└── prp-manager/ # THE SKILL (this is what users install)
├── SKILL.md # Main skill definition with frontmatter and workflows
├── assets/
│ └── templates/
│ └── prp_base.md # Default PRP template
└── references/
├── examples.md # Usage examples showing the three workflows
└── customization.md # Stack-specific validation commands
Important: Only the prp-manager/ subdirectory is the actual skill. The root-level files (README, LICENSE, CLAUDE.md) are for repository documentation and should not be copied when installing the skill.
Key Concepts
PRPs (Product Requirements Prompts): Implementation blueprints for AI that include product requirements, curated codebase intelligence, and agent runbooks with validation steps.
Context Engineering: A discipline for providing AI with comprehensive information needed to complete tasks end-to-end, including documentation, examples, rules, patterns, and validation mechanisms.
Three Workflows
- Initialize (
PRPs/templates/prp_base.md) - Analyzes project files to create a customized PRP template with project-specific validation commands - Generate (
PRPs/NNN--feature-name.md) - Creates comprehensive PRPs for new features using the project template - Execute - Implements features following PRP instructions with validation loops
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.
- 6d ago First seen · 49 lines · 563 tokens per session scan A 2e025327010a
prp-manager CLAUDE.md is an instructions file published in the GitHub repository willywg/prp-manager (14 stars, last pushed 7mo ago), licensed MIT. It adds 563 tokens to every session, about $0.0028 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 2026-08-30.
Other instructions, from other repositories
Atomic-Spec AGENTS.md
Instructions for Chappygo-OS/Atomic-Spec, covering agents.md — adding a new ai agent to atomic spec, about atomic spec and the atomicspec cli, general practices, adding new agent support and current supported agents.
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.
superpowers-zh CLAUDE.md
Claude Code instructions for jnMetaCode/superpowers-zh, covering superpowers — 贡献者指南, 如果你是 ai agent, pull request 要求, 我们不会接受的内容 and 第三方依赖.
spec-kit-zh AGENTS.md
AGENTS.md instructions for loulanyue/spec-kit-zh, covering agents.md, about spec kit and specify, general practices, adding new agent support and current supported agents.
nopua AGENTS.md
Instructions for wuji-labs/nopua, covering nopua · codex 入仓规则, 一 · 项目定位, 二 · 起手必读, 三 · 工程与研究纪律 and 四 · 对外署名.
claude-code-blueprint CLAUDE.md
Instructions for faizkhairi/claude-code-blueprint, covering global claude behavior rules, verify-after-complete (mandatory), what to verify depends on what was built, verification mindset and after verification.