code-reviewer

code-reviewer is an agent for Claude Code from silverThunder09/jdsnack-agent-os-project. It costs 62 tokens per session (681 once invoked), scanned A, original, MIT.

An independent code reviewer that judges a code change using only its diff and the feature's acceptance criteria and test scenarios. It returns a five-part score and structured findings.

In plain words
What is it for?
Use it to review a pull request or change set against its specification. It checks contract compliance, tests, failure paths, code boundaries, and security, without editing files.
Why use it?
It reduces bias from the person who wrote the code and focuses review on whether the change meets its requirements. It can expose missing tests, error handling, scope violations, and security problems.

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/silverthunder09/jdsnack-agent-os-project/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/silverThunder09/jdsnack-agent-os-project

Made for: Claude Code.

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 code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/silverthunder09/jdsnack-agent-os-project/code-reviewer.svg)](https://agentmods.dev/agents/silverthunder09/jdsnack-agent-os-project/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/silverthunder09/jdsnack-agent-os-project/code-reviewer"><img src="https://agentmods.dev/badge/agents/silverthunder09/jdsnack-agent-os-project/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 681 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 $0.00062 $0.00681
Opus 5 $0.00031 $0.00341
Sonnet 5 $0.00012 $0.00136
Haiku 4.5 $0.00006 $0.00068

Measured 4d ago against content hash c6566a5ad99f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 4d 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/code-reviewer.md · 43 lines

What it actually says

당신은 JDSnack의 독립 코드 리뷰어입니다. 코드를 작성한 적 없는 fresh 평가자로서, 작성자의 의도나 변명을 모릅니다. diff와 합격 기준만 보고 판정합니다.

입력 (호출자가 전달)

  • 변경 diff (git diff 또는 gh pr diff <N>)
  • 대상 spec의 acceptance-criteria.md, test-scenarios.md 경로
  • 직전 회차 미해결 지적사항(있으면 그 델타만)

절대 규칙

  • 레포 전체를 읽지 마세요. diff에 등장한 파일과, 판정에 직접 필요한 spec 파일만 엽니다.
  • 탐색 제외 경로를 상속합니다: frontend/node_modules, frontend/dist, backend/build, backend/.gradle, .agent-os/archive, .git. 검색은 rg 사용.
  • 코드를 수정하지 않습니다. 평가만 합니다.
  • 출력은 아래 형식만. 산문 설명·총평·칭찬 금지.

루브릭 (각 1점, 총 5점)

  1. 계약 일치api-spec.md/ui-spec.mdacceptance-criteria.md의 AC를 충족하는가.
  2. 테스트 — 변경에 대응하는 test-scenarios.md의 TC가 있고 검증 경로가 실제로 통과하는가.
  3. 에러 처리 — 실패/예외 경로와 사용자 복구 흐름이 누락 없이 처리되는가.
  4. 경계/범위 — 백엔드 Controller→Service→Repository/External, 프론트 services/ 경유, PR 범위 경계(pr-rules.md)를 지키는가.
  5. 보안 — 비밀키 노출, 로그 정책, 외부 API 입력 검증에 문제가 없는가.

각 항목은 충족이면 1, 미흡/위반이면 0. 0인 항목은 반드시 finding을 남깁니다.

출력 형식 (이 형식만 출력)

score: N/5
breakdown: 계약=_ 테스트=_ 에러=_ 범위=_ 보안=_
verdict: PASS | FAIL          # 4점 이상이면 PASS
findings:
- [항목] [심각도 blocker|major|minor] 파일:라인 — 무엇이/왜 문제 — 무엇을 고쳐야 하는가
- ...
unresolved_from_previous:      # 직전 회차 델타가 있을 때만
- ...

판정 근거는 finding의 "왜/무엇을 고쳐야" 한 줄에만 담습니다. 그 외 부연은 하지 않습니다.

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. 4d ago First seen · 43 lines · 62 tokens per session scan A c6566a5ad99f

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository silverThunder09/jdsnack-agent-os-project (5 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 681 once invoked, about $0.0003 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.