PRP is a collection of prompts and workflows for AI-assisted software development with Claude Code. Its Product Requirement Prompts combine product requirements, selected codebase context, and an execution runbook so a coding agent can implement a vertical slice of software. The catalogue entries are the project’s own skills, agents, instructions, hook, and plugin workflows.
Borrowing it
Nothing to install: this file belongs to Wirasm/prp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Wirasm/prp/development/.agents/skills/prp-meta-skill/SKILL.mdgit clone --depth 1 https://github.com/Wirasm/prpWrote 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/skills/wirasm/prp/prp-meta-skill)<a href="https://agentmods.dev/skills/wirasm/prp/prp-meta-skill"><img src="https://agentmods.dev/badge/skills/wirasm/prp/prp-meta-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wirasm/prp/prp-meta-skill"><img src="https://agentmods.dev/badge/skills/wirasm/prp/prp-meta-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00080 | $0.01579 |
| Opus 5.5 | $0.00032 | $0.00632 |
| Sonnet 5.5 | $0.00016 | $0.00316 |
| Haiku 4.5 | $0.00008 | $0.00158 |
Grade A, and why
prp-meta-skill 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 1mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRP Meta-Skill — Author, Refactor & Consolidate Skills
A PRP-style runbook for three jobs:
- Create a new skill from scratch (or from an existing command/prompt).
- Refactor an existing skill — split detail into
references/, move output formats intotemplates/, and trimSKILL.mdto a lean spine of pointers. - Consolidate overlapping workflows — trace their contracts, choose one composition owner, reuse specialist skills, and retire duplicate paths without losing outcomes or human gates.
This skill is built the way it teaches: a lean body that defers detail to references/. Follow that example.
Prescribe the craft, not the content
This skill is opinionated about how to build a skill well and deliberately agnostic about what any given skill — or the artifact it produces — should contain.
- Prescribe (firm, universal): progressive disclosure, third-person trigger-rich descriptions, imperative body, no-duplication, lean body, every reference wired, deliberate invocation control, validation that fits. See
references/skill-standards.md. - Do NOT prescribe (per-project, the author's call): the sections a plan / PRD / report should contain, what a project's template looks like, which phases exist, the domain vocabulary. There is no canonical output shape — guide the author to a good decision, never hand them a fixed one.
Restrictions are not rigidity: be strict on the craft so the author stays free on the content.
The PRP lens — applied to the skill type
Classify the skill first (workflow / artifact-generator / knowledge-reference / tool-wrapper — see references/skill-standards.md → Skill types), then apply only the principles that fit:
- Context is King — give the agent ALL the context it needs (patterns, gotchas, schemas, examples) via whichever source fits: inline, bundled and disclosed on demand, pointed to by file path or URL, or gathered from the user at runtime. Curate it — don't dump it. (
references/skill-standards.md→ Context sources.) - Validation that fits — workflow skills ship verifiable gates, and prefer an external, authoritative check (exit code, file presence) over the agent's own "done" sentinel. A knowledge/reference skill has nothing to validate — don't bolt a loop onto it.
- Information dense — real trigger phrases, real examples, real
file:line. No filler, no restating what the model already knows. - Progressive success — ship the smallest complete SKILL.md that triggers correctly first, validate, then enrich with references. Don't build all the references before the spine works.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 78 lines · 80 tokens per session scan A 3f8c007fde46
prp-meta-skill is a skill published in the GitHub repository Wirasm/prp (2,264 stars, last pushed 18d ago), licensed MIT. It adds 80 tokens to every session and 1,579 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…