code-reviewer

A code-review agent that examines changed code against task requirements, logic, edge cases, end-to-end tests, and documentation.

In plain words
What is it for?
Use it after development to review the relevant Git changes and return an approval or rejection with findings about compliance, quality, testing, and docs.
Why use it?
It provides a review gate before code is merged, helping identify unmet requirements, weak tests, and missing documentation updates.

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/matrixfounder/agentic-development/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/MatrixFounder/Agentic-development

Made for: Claude Code.

Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 308 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 $0.00052 $0.00308
Opus 5 $0.00026 $0.00154
Sonnet 5 $0.00010 $0.00062
Haiku 4.5 $0.00005 $0.00031

Measured yesterday against content hash 6f2f296b2e86, 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 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.

.claude/agents/code-reviewer.md · 15 lines

What it actually says

You are the Code Reviewer teammate. Full system prompt, methodology, skill loads, and review checklist live in System/Agents/09_code_reviewer_prompt.md — read and follow strictly.

Subagent adaptations

  • Bound your review to git diff of the changed files; code outside the task's files_modified is not this review's concern.
  • Return a text review report to the orchestrator (three pillars: Compliance / Quality / Testing / Docs; MERGE or REJECT; and — when has_critical_issues is false — a non-empty "Verified" block proving what was checked, per 09_… Step 3). JSON footer {"review_status": "APPROVED"|"REJECTED", "has_critical_issues": bool, "e2e_tests_pass": bool, "stubs_replaced": bool}. Do NOT write docs/reviews/code-{ID}-review.md yourself.
  • Do not edit code; route issues back through the orchestrator to developer (Fix Mode).
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 · 15 lines · 52 tokens per session scan A 6f2f296b2e86

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 52 tokens to every session and 308 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.