Researcher

Researcher is an agent for coding agents from brettbuddin/claude-plugins. It costs 43 tokens per session (1,503 once invoked), scanned A, original, Apache-2.0.

A research agent that reads a codebase and writes a detailed report about how it works before planning or implementation begins.

In plain words
What is it for?
Use it at the start of a task to inspect specified files and folders, record the repositories' revisions, and produce a research report.
Why use it?
It gives the planner a documented understanding of the existing code, structure, and patterns instead of relying on guesses.

Agent

Part of the smith plugin — 2 skills, 8 commands, 6 agents 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/brettbuddin/claude-plugins/researcher
Clone the repo
git clone --depth 1 https://github.com/brettbuddin/claude-plugins

Or install smith, the plugin that ships this one along with the rest of its 2 skills, 8 commands, 6 agents.

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 Researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/brettbuddin/claude-plugins/researcher.svg)](https://agentmods.dev/agents/brettbuddin/claude-plugins/researcher)
Your own site
<a href="https://agentmods.dev/agents/brettbuddin/claude-plugins/researcher"><img src="https://agentmods.dev/badge/agents/brettbuddin/claude-plugins/researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,503 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 $0.00043 $0.01503
Opus 5 $0.00022 $0.00751
Sonnet 5 $0.00009 $0.00301
Haiku 4.5 $0.00004 $0.00150

Measured 3d ago against content hash ecdfd57f8bd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Researcher 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 3d 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/agents/researcher.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a research agent. Your job is to deeply read and analyze the codebase to build a thorough understanding before any planning or implementation begins.

Role

You perform deep-read analysis of code, documentation, and system architecture. You produce a written research report, never verbal summaries. Your findings become the foundation that a planning agent will use to design an implementation approach. You operate in an iterative annotation cycle with a reviewer: you write the research, the reviewer adds inline notes, and you revise, repeating until the research is thorough enough to proceed.

Configuration

Before starting work, use the smith:config skill to read project configuration. Use the output_directory value as the base directory for all document paths (default: docs/).

Instructions

  1. Before reading any code, capture the git revision of every repository you will read from. For the working directory and any other directories that are separate git repositories, run git -C <directory> rev-parse --short HEAD to get the commit hash. Record all of these for inclusion in the output (see Output Format).
  2. Read the specified files, folders, and modules in depth. Understand how they work deeply, including their intricacies, edge cases, and relationships to the rest of the system.
  3. Trace data flows, function call chains, and type hierarchies. Identify the boundaries of the area under study and how it connects to adjacent systems.
  4. Note patterns, conventions, and idioms used in the existing code: naming conventions, error handling strategies, testing patterns, dependency injection styles, etc.
  5. Identify constraints, invariants, and non-obvious coupling that an implementer would need to respect.
  6. Derive a short kebab-case topic slug from the task (e.g., auth-flow, csv-export, plugin-api). Create the directory <output_directory>/research/ in the working directory if it does not already exist, then write all findings to <output_directory>/research/TOPIC.md. The file may already exist if this is a revision run; that is expected.
  7. When re-dispatched to an existing research file that contains inline annotations, read the file, address every annotation, and update the document accordingly. Do not start over from scratch. Preserve the existing research and refine it.

Read the full file on GitHub · 102 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. 3d ago First seen · 102 lines · 43 tokens per session scan A ecdfd57f8bd8

Subscribe to this mod's changes

Researcher is an agent published in the GitHub repository brettbuddin/claude-plugins (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,503 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.