paul:research

paul:research is a command for coding agents from ChristopherKahler/paul. It costs 13 tokens per session (351 once invoked), scanned A, original, MIT.

A research command that investigates a topic with supporting sub-agents. It can focus on the codebase, web documentation, or choose an approach automatically.

In plain words
What is it for?
Use it to research a technical question, inspect a repository, or gather web and documentation findings before deciding what to build.
Why use it?
It divides research into suitable independent tasks and saves the findings, so exploration is organized before planning or implementation begins.

Command

About the project

PAUL is a structured development workflow for Claude Code that organizes AI-assisted work into planning, implementation, and state-reconciliation steps. It is for developers who want acceptance criteria, managed context, and completed plans while building software with Claude Code. Its catalogue entries are commands that implement the workflow.

ChristopherKahler/paul · 1,212 stars · on GitHub

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/christopherkahler/paul/research
Clone the repo
git clone --depth 1 https://github.com/ChristopherKahler/paul

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 paul:research

README.md
[![agentmods](https://agentmods.dev/badge/commands/christopherkahler/paul/research.svg)](https://agentmods.dev/commands/christopherkahler/paul/research)
Your own site
<a href="https://agentmods.dev/commands/christopherkahler/paul/research"><img src="https://agentmods.dev/badge/commands/christopherkahler/paul/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 351 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 $0.00013 $0.00351
Opus 5 $0.00006 $0.00176
Sonnet 5 $0.00003 $0.00070
Haiku 4.5 $0.00001 $0.00035

Measured 5d ago against content hash 99624c641ee9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

paul: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.

src/commands/research.md · 48 lines

What it actually says

When to use: When you need to gather information on a topic before planning or implementing.

Subagent use case: Research is the APPROPRIATE use of subagents per subagent-criteria.md:

  • Task Independence: Research is self-contained
  • Clear Scope: Topic defines clear inputs/outputs
  • Parallel Value: Multiple topics can run simultaneously
  • Complexity Sweet Spot: 15-30 min per research task

<execution_context> @/.claude/paul-framework/workflows/research.md @/.claude/paul-framework/references/subagent-criteria.md </execution_context>

Optional flags:

  • --codebase: Focus on codebase exploration (uses Explore agent)
  • --web: Focus on web/documentation (uses general-purpose agent)
  • No flag: Auto-detect based on topic

@.paul/PROJECT.md @.paul/STATE.md

<success_criteria>

  • Topic validated (not trivial)
  • Appropriate agent type selected
  • Subagent spawned for research
  • Findings saved to .paul/research/{topic}.md
  • Summary presented for review </success_criteria>
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 · 48 lines · 13 tokens per session scan A 99624c641ee9

Subscribe to this mod's changes

paul:research is a command published in the GitHub repository ChristopherKahler/paul (1,212 stars, last pushed 13d ago), licensed MIT. It adds 13 tokens to every session and 351 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 2026-08-30.