research

research is a command for coding agents from benshapyro/cadre-devkit-claude. It costs 10 tokens per session (1,032 once invoked), scanned A, original, MIT.

A research command that coordinates several parallel helpers to investigate a topic and combine their findings. It can consider the codebase, documentation, architecture, infrastructure, and community practices as relevant.

In plain words
What is it for?
Use it for broad technical investigations involving existing code, frameworks, libraries, APIs, system design, or development practices.
Why use it?
It helps cover multiple research angles and identify knowledge gaps before making a technical decision.

Command

Part of the cadre-devkit-claude plugin — 10 skills, 10 commands, 7 agents, 3 hooks 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 commands/benshapyro/cadre-devkit-claude/research
Clone the repo
git clone --depth 1 https://github.com/benshapyro/cadre-devkit-claude

Or install cadre-devkit-claude, the plugin that ships this one along with the rest of its 10 skills, 10 commands, 7 agents, 3 hooks.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/benshapyro/cadre-devkit-claude/research.svg)](https://agentmods.dev/commands/benshapyro/cadre-devkit-claude/research)
Your own site
<a href="https://agentmods.dev/commands/benshapyro/cadre-devkit-claude/research"><img src="https://agentmods.dev/badge/commands/benshapyro/cadre-devkit-claude/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,032 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 $0.00010 $0.01032
Opus 5 $0.00005 $0.00516
Sonnet 5 $0.00002 $0.00206
Haiku 4.5 $0.00001 $0.00103

Measured 5d ago against content hash 0118082e840a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research 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 5d 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.

commands/research.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Command

Orchestrate comprehensive research using multiple parallel sub-agents.

Validation

If no topic provided, ask for one.

Research Flow

1. Analyze Request

Before proposing a research plan:

  • Understand the user's question/topic
  • Consider the project context (CLAUDE.md, tech stack, existing patterns)
  • Review conversation history for relevant context
  • Identify knowledge gaps that need filling

2. Propose Research Plan

Suggest a tailored research plan. Dynamically determine which research agents are needed:

Possible Research Dimensions:

Dimension When to Include
Codebase - Existing Patterns Feature touches existing code
Codebase - Architecture Architectural decision needed
Codebase - Frontend UI/UX or frontend changes
Codebase - Backend API/database/server changes
Codebase - Infrastructure DevOps, deployment, CI/CD
Documentation - Framework Using framework features
Documentation - Libraries Using external libraries
Documentation - APIs Integrating external services
Community - Best Practices Common patterns and anti-patterns
Community - Recent Changes Library updates, deprecations

Output Format:

## Research Plan: [topic]

Based on your question and this project's context, I recommend:

### Proposed Research Agents (N)

1. **[Category] [Specific Focus]**
   - What: [What this agent will investigate]
   - Why: [Why this is relevant to your question]

2. **[Category] [Specific Focus]**
   - What: [description]
   - Why: [relevance]

[...more as needed...]

### Questions Before Proceeding

- [Any clarifying question if the request is ambiguous]

---
Proceed with this plan? (yes / adjust / add more / cancel)

3. Await Approval

Wait for user to:

  • Approve ("yes", "proceed", "looks good")
  • Adjust ("skip the community one", "also check X")
  • Add ("also research Y")
  • Cancel ("nevermind")

Read the full file on GitHub · 170 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. 5d ago First seen · 170 lines · 10 tokens per session scan A 0118082e840a

Subscribe to this mod's changes

research is a command published in the GitHub repository benshapyro/cadre-devkit-claude (9 stars, last pushed 9mo ago), licensed MIT. It adds 10 tokens to every session and 1,032 once invoked, about $0.0001 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 2026-08-31.