research

A research command that investigates a development question using documentation, web searches, codebase exploration, and separate research agents working in parallel.

In plain words
What is it for?
Use it to investigate technical problems, find recommended patterns, identify common pitfalls, and understand how a question relates to an existing codebase.
Why use it?
It gathers information from several places so you do not have to search documentation, public discussions, and the codebase separately.

Command for Claude Code

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/wbern/agent-instructions/research
Clone the repo
git clone --depth 1 https://github.com/wbern/agent-instructions

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 727 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 $0.00021 $0.00727
Opus 5 $0.00010 $0.00364
Sonnet 5 $0.00004 $0.00145
Haiku 4.5 $0.00002 $0.00073

Measured 2d ago against content hash bbbd0fff1b8d, 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 2d 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/commands/research.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

General Guidelines

Output Style

  • Never explicitly mention TDD in code, comments, commits, PRs, or issues
  • Write natural, descriptive code without meta-commentary about the development process
  • The code should speak for itself - TDD is the process, not the product

Beads is available for task tracking. Use mcp__beads__* tools to manage issues (the user interacts via bd commands).

User arguments:

Research: $ARGUMENTS

End of user arguments

Research the following problem or question thoroughly, like a senior developer would.

Step 1: Launch Parallel Research Agents

Use the Task tool to spawn these subagents in parallel (all in a single message):

  1. Web Documentation Agent (subagent_type: general-purpose)

    • Search official documentation for the topic
    • Find best practices and recommended patterns
    • Locate relevant GitHub issues or discussions
  2. Web Search Agent (subagent_type: general-purpose)

    • Perform broad web searches for solutions and discussions
    • Find Stack Overflow answers, blog posts, and tutorials
    • Note common pitfalls and gotchas
  3. Codebase Explorer Agent (subagent_type: Explore)

    • Search the codebase for related patterns
    • Find existing solutions to similar problems
    • Identify relevant files, functions, or components

Step 2: Library Documentation (Optional)

If the research involves specific frameworks or libraries:

  • Use Context7 MCP tools (mcp__context7__resolve-library-id, then get-library-docs)
  • Get up-to-date API references and code examples
  • If Context7 is unavailable, note this in findings so user knows library docs were harder to obtain

Step 3: Deep Analysis

With all gathered context, perform extended reasoning (ultrathink) to:

  • Analyze the problem from first principles
  • Consider edge cases and trade-offs
  • Synthesize insights across all sources
  • Identify conflicts between sources

Step 4: Present Findings

Present a structured summary to the user:

Read the full file on GitHub · 108 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. 2d ago First seen · 108 lines · 21 tokens per session scan A bbbd0fff1b8d

Subscribe to this mod's changes

research is a command published in the GitHub repository wbern/agent-instructions (168 stars, last pushed 3mo ago), licensed MIT. It adds 21 tokens to every session and 727 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.