prp: Skill for Claude Code

.claude/skills/prp-research-team/SKILL.md

prp-research-team is a skill for Claude Code from Wirasm/prp. It costs 54 tokens per session (4,730 once invoked), scanned A, original, MIT.

A planning tool for dividing a research question among several software agents. It creates a team structure and an executable plan, but does not perform the research itself.

In plain words
What is it for?
Use it to plan multi-agent research on subjects such as markets, technology, or codebase architecture. It produces a structured plan for Claude Code's experimental agent-teams feature.
Why use it?
It turns a broad question into focused assignments with completion rules and expected outputs. The team is shaped around the topic instead of using the same fixed set of researchers every time.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents; mentions Claude Code.

This is Wirasm/prp's own configuration. It tells Claude Code how to work on prp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything prp configures →

View source ↗ Wirasm/prp
About the project

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.

Wirasm/prp · 2,242 stars · on GitHub

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/Wirasm/prp/development/.claude/skills/prp-research-team/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Wirasm/prp

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 prp-research-team

README.md
[![agentmods](https://agentmods.dev/badge/skills/wirasm/prp/prp-research-team.svg)](https://agentmods.dev/skills/wirasm/prp/prp-research-team)
Your own site
<a href="https://agentmods.dev/skills/wirasm/prp/prp-research-team"><img src="https://agentmods.dev/badge/skills/wirasm/prp/prp-research-team.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,730 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00054 $0.04730
Opus 5 $0.00027 $0.02365
Sonnet 5 $0.00011 $0.00946
Haiku 4.5 $0.00005 $0.00473

Measured 8d ago against content hash 0cabc8c15b31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

prp-research-team 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 8d 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/skills/prp-research-team/SKILL.md · 541 lines

How it starts

The opening of the file, as written. The whole thing — 541 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PRP Research Team Planner

Input: $ARGUMENTS


Mission

Design a dynamic team of research agents and a structured research plan for any given question or topic. The plan targets Claude Code's experimental agent teams feature (TeamCreate, shared task list, delegate mode).

Core Principle: PLAN ONLY — no research is executed. Produce a comprehensive, executable research plan that enables a team of agents to deliver thorough findings.

Golden Rule: Every researcher must have a clear focus, measurable completion criteria, and a defined output format. No vague mandates.

Doctrine: The research question dictates the team — never force a fixed roster. A market research question demands different expertise than a codebase architecture question.


Variables

Variable Source Default
$ARGUMENTS User input — (required)
ORCHESTRATION --orchestration "..." flag in $ARGUMENTS Empty (auto-compose)
OUTPUT_DIR Fixed $PRP_DIR/research-plans/

Phase 1: PARSE — Extract Research Question

1.1 Parse Arguments

Extract from $ARGUMENTS:

  • Research question or topic: Everything that is NOT a flag
  • Orchestration guidance: Value after --orchestration flag (if present)

Parsing rules:

  1. Strip --orchestration "..." or --orchestration '...' from arguments → store as ORCHESTRATION
  2. Remaining text = research question
  3. If question is empty after parsing → STOP with error

1.2 Identify Scope Signals

Scan the research question for scope indicators:

Signal Example Implication
Comparative ("vs", "compare", "alternatives") "React vs Vue vs Svelte" Multiple perspectives needed
Evaluative ("best", "optimal", "should we") "Best approach for real-time sync" Criteria definition needed
Exploratory ("how", "what are", "landscape") "What are the approaches to..." Broad survey needed
Investigative ("why", "root cause", "debug") "Why does X fail under Y" Deep-dive analysis needed
Quantitative ("benchmark", "performance", "cost") "Performance cost of SSR" Measurement methodology needed

Read the full file on GitHub · 541 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. 8d ago First seen · 541 lines · 54 tokens per session scan A 0cabc8c15b31

Subscribe to this mod's changes

prp-research-team is a skill published in the GitHub repository Wirasm/prp (2,242 stars, last pushed 6d ago), licensed MIT. It adds 54 tokens to every session and 4,730 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens