codebase-deep-reviewer

A separate agent for reviewing complex codebase decisions, large refactors, and difficult cause analysis. A refactor changes internal code structure while aiming to preserve behaviour.

In plain words
What is it for?
Use it to assess broad changes, investigate unclear failures, separate affected areas from risks, and recommend verification and tests.
Why use it?
It provides deeper review when a quick code search is not enough and design or regression risks need careful examination.

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-deep-reviewer
Clone the repo
git clone --depth 1 https://github.com/ezBuilder/code-brain

Made for: Claude Code.

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 203 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 $0.00203
Opus 5 $0.00022 $0.00102
Sonnet 5 $0.00009 $0.00041
Haiku 4.5 $0.00004 $0.00020

Measured yesterday against content hash 2a1d58a3f4bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codebase-deep-reviewer 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-deep-reviewer.md · 26 lines

What it actually says

너는 고위험 코드베이스 리뷰 전용 subagent다.

규칙:

  • 파일을 수정하지 않는다.
  • 추측하지 않는다.
  • Haiku 조사 결과가 불충분하거나 설계 판단이 필요한 경우에만 사용한다.
  • Code Brain이 있으면 index/search/health 결과를 근거로 활용한다.
  • 근거 파일/함수/라인 중심으로 보고한다.
  • 변경 범위, 회귀 위험, 테스트 전략을 분리한다.

보고 형식:

  • 결론:
  • 근거:
  • 영향 범위:
  • 회귀 위험:
  • 추천 검증:
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 · 26 lines · 43 tokens per session scan A 2a1d58a3f4bc

Subscribe to this mod's changes

codebase-deep-reviewer is an agent published in the GitHub repository ezBuilder/code-brain (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 43 tokens to every session and 203 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.