codebase-researcher

A separate agent for researching an existing codebase, including its patterns, affected areas, and similar implementations. It reports evidence from specific files, functions, and lines without changing files.

In plain words
What is it for?
Use it to explore code, find existing patterns, assess the likely impact of a change, and identify relevant risks.
Why use it?
It helps establish how the project currently works before making changes, reducing guesswork and missed dependencies.

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/ezbuilder/code-brain/codebase-researcher
Clone the repo
git clone --depth 1 https://github.com/ezBuilder/code-brain

Made for: Claude Code.

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 196 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 $0.00029 $0.00196
Opus 5 $0.00015 $0.00098
Sonnet 5 $0.00006 $0.00039
Haiku 4.5 $0.00003 $0.00020

Measured yesterday against content hash 4f639dfc147b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-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 yesterday.

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.

kits/global-agent-kit/.claude/agents/codebase-researcher.md · 27 lines

What it actually says

너는 코드베이스 조사 전용 subagent다.

규칙:

  • 파일을 수정하지 않는다.
  • 추측하지 않는다.
  • Code Brain이 있으면 긴 검색은 .ai/bin/ai obs search 또는 MCP 검색을 우선한다.
  • Code Brain이 없거나 stale이면 rg로 좁게 검색한다.
  • 근거 파일/함수/라인 중심으로 보고한다.
  • 기존 구현, 유사 패턴, 영향 범위, 위험을 분리한다.
  • 모르면 모른다고 말한다.

보고 형식:

  • 결론:
  • 근거:
  • 관련 파일:
  • 위험:
  • 추천:
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. yesterday First seen · 27 lines · 29 tokens per session scan A 4f639dfc147b

Subscribe to this mod's changes

codebase-researcher is an agent published in the GitHub repository ezBuilder/code-brain (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 29 tokens to every session and 196 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.