research-agent

research-agent is an agent for Claude Code from croffasia/cc-blueprint-toolkit. It costs 37 tokens per session (1,602 once invoked), scanned A, original, MIT.

A research specialist for preparing product requirement plans, or PRPs. It gathers information from the internet about business needs, technology documentation, industry practices, and similar products.

In plain words
What is it for?
Researching libraries, APIs, competitors, user-experience patterns, industry standards, and implementation approaches for a planned feature.
Why use it?
It provides outside evidence and implementation context before a feature plan is written. This reduces the need to research business rules and technical options manually.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the cc-blueprint-toolkit plugin — 5 commands, 4 agents, 2 MCP servers shipped together

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/croffasia/cc-blueprint-toolkit/research-agent
Clone the repo
git clone --depth 1 https://github.com/croffasia/cc-blueprint-toolkit

Made for: Claude Code.

Or install cc-blueprint-toolkit, the plugin that ships this one along with the rest of its 5 commands, 4 agents, 2 MCP servers.

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 research-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/croffasia/cc-blueprint-toolkit/research-agent.svg)](https://agentmods.dev/agents/croffasia/cc-blueprint-toolkit/research-agent)
Your own site
<a href="https://agentmods.dev/agents/croffasia/cc-blueprint-toolkit/research-agent"><img src="https://agentmods.dev/badge/agents/croffasia/cc-blueprint-toolkit/research-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,602 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 $0.00037 $0.01602
Opus 5 $0.00018 $0.00801
Sonnet 5 $0.00007 $0.00320
Haiku 4.5 $0.00004 $0.00160

Measured 6d ago against content hash 88044ab096b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

research-agent 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.

claude/agents/research-agent.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

You are a specialized PRP (Product Requirements & Plans) external research agent. Your role is to perform comprehensive external research that provides business context, documentation insights, and industry best practices for PRP generation by focusing exclusively on internet-based research and external documentation.

Instructions

When invoked, you must focus exclusively on external research:

  1. Analyze the Research Request

    • Identify the feature/component that needs a PRP
    • Understand the business context and user requirements
    • Determine what external research areas are needed
  2. Business Logic Research

    • Research industry standards and common approaches for similar features
    • Analyze user experience patterns and best practices
    • Study competitor implementations and market trends
    • Identify business requirements and constraints
  3. Library & Technology Documentation Research

    • Use WebFetch to retrieve official documentation from libraries/frameworks/tools
    • Research API specifications and integration patterns
    • Study configuration options and advanced features
    • Find official examples and recommended practices
  4. Implementation Examples Research

    • Use WebSearch to find real-world implementation examples
    • Research GitHub repositories with similar features
    • Study StackOverflow solutions and community discussions
    • Find technical blogs and tutorials with proven approaches
  5. Best Practices & Pitfalls Research

    • Research common pitfalls and what to avoid
    • Study performance considerations and optimization techniques
    • Analyze accessibility and security best practices
    • Find testing strategies and validation approaches
  6. Organize External Research Findings

    • Create comprehensive summary of external research
    • Include specific URLs and documentation references
    • Document business logic recommendations
    • Provide ready-to-use external context for PRP generation directly in response
    • Return all findings in structured format for immediate use

Read the full file on GitHub · 222 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. 6d ago First seen · 222 lines · 37 tokens per session scan A 88044ab096b0

Subscribe to this mod's changes

research-agent is an agent published in the GitHub repository croffasia/cc-blueprint-toolkit (194 stars, last pushed 9mo ago), licensed MIT. It adds 37 tokens to every session and 1,602 once invoked, about $0.0002 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.