research

A command that sends a named research request to a Researcher agent and produces a written report about that area of the codebase.

In plain words
What is it for?
Use it when you need research on a specific topic or part of a project before planning or implementation.
Why use it?
It creates a repeatable way to begin technical investigation and can also examine the history of important files when configured to do so.

Command

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/brettbuddin/claude-plugins/research
Clone the repo
git clone --depth 1 https://github.com/brettbuddin/claude-plugins
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 445 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 $0.00032 $0.00445
Opus 5 $0.00016 $0.00222
Sonnet 5 $0.00006 $0.00089
Haiku 4.5 $0.00003 $0.00044

Measured 2d ago against content hash 26a084f17068, 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.

smith/commands/research.md · 50 lines

What it actually says

Research

Dispatch the Researcher agent to produce a research report, then run git history analysis on the key paths it identified.

Args

<topic/area description> (required). If no description is provided, reply with a short usage summary and stop.

Steps

Configuration

  1. Use the smith:config skill to read project configuration. Use the output_directory value (default: docs/) wherever <output_directory> appears below.

Phase 1: Research

  1. Use the Task tool with subagent_type: "Researcher" and run_in_background: false.
  2. Prompt the agent with the topic/area description provided by the user.
  3. After completion, note the research file path (e.g., <output_directory>/research/TOPIC.md).

Phase 2: History

Skip this phase if the research_history configuration option is false.

  1. Read the research file produced in Phase 1. Extract the key file and directory paths from the Key Components and Architecture sections.
  2. Use the Task tool with subagent_type: "Historian" and run_in_background: false.
  3. Prompt the agent with:
    • The absolute path to the research file.
    • The list of key paths extracted in step 4.

Wrap-Up

  1. Tell the user the research file path and suggest they review it, annotate it if needed and run /revise-research, or proceed to /plan <goal>.

Prompting the Agents

When constructing the prompt for the Task tool, include:

  • The user's description (Phase 1) or key paths (Phase 2)
  • The working directory path so the agent knows where to find/write files
  • Any additional context the user provided in the conversation

Do NOT paste the agent's own instructions into the prompt; the agent definitions are already loaded by the Task tool via subagent_type.

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 · 50 lines · 32 tokens per session scan A 26a084f17068

Subscribe to this mod's changes

research is a command published in the GitHub repository brettbuddin/claude-plugins (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 445 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 2026-08-31.