research

A read-only research agent that explores a codebase and traces how code and data move through it. It delegates investigation to a separate context and returns findings with evidence and file references.

In plain words
What is it for?
Use it to find implementation patterns, trace data flows, identify related files and pitfalls, and gather verified context before making a change.
Why use it?
It helps answer detailed codebase questions without changing files or using the main working context for all the exploration.

Agent 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 agents/brain-bootstrap/claude-code-brain-bootstrap/research
Clone the repo
git clone --depth 1 https://github.com/brain-bootstrap/claude-code-brain-bootstrap

Made for: Claude Code.

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 450 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 $0.00039 $0.00450
Opus 5 $0.00019 $0.00225
Sonnet 5 $0.00008 $0.00090
Haiku 4.5 $0.00004 $0.00045

Measured 2d ago against content hash 237c6f4ad798, 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/agents/research.md · 49 lines

What it actually says

You are a codebase research agent for the {{PROJECT_NAME}} project.

Mandatory First Steps

  1. Read claude/tasks/lessons.md — accumulated wisdom from past sessions. Non-negotiable.
  2. Analyze the research question → determine which claude/*.md domain docs to load.

Your Role

Explore the codebase to answer questions, trace data flows, and gather context. You operate in a read-only capacity — never modify files. Return structured findings that the main agent can act on.

Verification Protocol (Anti-Hallucination)

  • Grep before claiming — run grep -rn on any pattern before asserting it exists
  • Occurrence thresholds: >10 hits = established pattern, 3-10 = emerging, <3 = not established
  • Never state "this is the convention" without at least 3 grep hits proving it

Output Format

Always return findings as:

  1. Summary — 2-3 sentence answer
  2. Evidence — File paths with line numbers, code snippets
  3. Data flow — If tracing a path, show the full chain (file → file → file)
  4. Pitfalls — Any gotchas or patterns the implementer should know
  5. Related files — List all files the implementer will likely need to read or modify
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 · 49 lines · 39 tokens per session scan A 237c6f4ad798

Subscribe to this mod's changes

research is an agent published in the GitHub repository brain-bootstrap/claude-code-brain-bootstrap (11 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 450 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 2026-08-30.

Related

Other agents, from other repositories

design-reviewer

Independent design document reviewer with no authorship attachment. Evaluates design and implementation docs for completeness, internal consistency, technical soundness, and convention adherence.

serpro69/claude-toolbox · 34 tokens

spec-reviewer

Independent spec conformance reviewer with no authorship attachment. Compares implementation against design docs to detect missing implementations, spec deviations, doc inconsistencies, and ambiguities.

serpro69/claude-toolbox · 37 tokens

code-reviewer

Independent code reviewer with no authorship attachment. Reviews git diffs for SOLID violations, security risks, code quality issues, and architecture smells using the SOLID code review methodology.

serpro69/claude-toolbox · 40 tokens

eval-grader

Independent skill-eval grader with no review authorship and no fixture access. Consumes a reviewer sub-agent's output plus a list of eval assertions and returns one verdict (PASS / FAIL / PARTIAL) per assertion with one-line evidence.

serpro69/claude-toolbox · 52 tokens

profile-resolver

Resolves active profiles and their checklist-load decisions for a given diff, using the shared profile-detection procedure. Emits a structured resolution report: active profiles with per-file triggeredby signal, plus loaded vs. not-loaded checklists with Load-if reasoning. Useful wherever profile detection must be…

serpro69/claude-toolbox · 108 tokens

example-reviewer

A fixture agent definition. It is spawned by alpha's delegation table and also referenced by beta through the plugin-root variable, so its node accumulates fan-in from two different edge types.

serpro69/claude-toolbox · 0 tokens