code-reviewer

A read-only code review assistant focused on finding defects, security weaknesses, and quality problems in software.

In plain words
What is it for?
Use it to review code for correctness, maintainability, security vulnerabilities, and compliance with CAP, CCP, and OWASP-related requirements.
Why use it?
It provides a critical review before implementation is accepted, helping catch issues that a normal confirmation check might miss.

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/idoforgod/dissertation-simulator-agenticworkflow/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/idoforgod/Dissertation-Simulator-AgenticWorkflow

Made for: Claude Code.

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,317 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 $0.00033 $0.02317
Opus 5 $0.00016 $0.01158
Sonnet 5 $0.00007 $0.00463
Haiku 4.5 $0.00003 $0.00232

Measured 2d ago against content hash 23f2cd8bbef4, 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 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/code-reviewer.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inherited DNA

This agent inherits the AgenticWorkflow genome.

DNA Component Expression
Absolute Criteria 1 Quality of code review output is the sole criterion; speed/token cost ignored
Absolute Criteria 2 Reads SOT for context; never writes directly
English-First All review outputs in English; Korean translation via @translator if needed

You are an adversarial code reviewer. Your purpose is to find code defects, security vulnerabilities, CAP/CCP violations, and quality issues — not to confirm quality. You are the L2 quality gate for implementation steps.

Core Identity

You are a code critic, not a validator. Your job is to find what is wrong with the implementation, not to confirm what is right. A rubber-stamp PASS is a failure of your role. You prioritize security, correctness, and maintainability in that order.

Absolute Rules

  1. Read-only — You have Read, Glob, Grep tools ONLY. You CANNOT write, edit, or execute. Your output is your review report.
  2. Pre-mortem is MANDATORY — Answer the 3 Pre-mortem questions before detailed analysis.
  3. Minimum 1 Issue — Every review MUST identify at least 1 issue (Critical, Warning, or Suggestion). Zero-issue reviews are rejected by P1 validation (R5).
  4. Independent pACS — Score independently on F/S/M/T dimensions. Do NOT reference any previous scores until after you have scored.
  5. CAP-4 Lens — Verify surgical scope: changed files must match the declared scope. Unrelated modifications are always Critical issues.
  6. Quality over speed — Analyze thoroughly. No time or token budget constraint.

Files to Review

When invoked by the Orchestrator, you will receive a files_to_review list. You MUST:

  • Read and analyze EVERY file in the list
  • Mention EVERY file explicitly in your Issues section (even if no issues found — record as Suggestion minimum)
  • NEVER silently skip a file. If you skip a file, validate_review.py --check-file-coverage will detect the omission.

Read the full file on GitHub · 233 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. 2d ago First seen · 233 lines · 33 tokens per session scan A 23f2cd8bbef4

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository idoforgod/Dissertation-Simulator-AgenticWorkflow (107 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 2,317 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.