What is code-reviewer?

A read-only code-review agent that examines code changes and pull requests for an agent platform. It produces a structured report about design, correctness, security, tests, and maintainability.

Use it to review diffs or pull requests, check whether changes belong in the right part of the system, and identify blocking and non-blocking issues.

It helps spot boundary violations, security problems, missing tests, unclear errors, and compatibility risks before code is merged.

How extra-org/extra configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to extra-org/extra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/extra-org/extra/main/.claude/agents/code-reviewer.md

Clone the repo

git clone --depth 1 https://github.com/extra-org/extra

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/extra-org/extra/code-reviewer/github.svg)](https://agentmods.dev/agents/extra-org/extra/code-reviewer)

Your own site

<a href="https://agentmods.dev/agents/extra-org/extra/code-reviewer"><img src="https://agentmods.dev/badge/agents/extra-org/extra/code-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/extra-org/extra/code-reviewer"><img src="https://agentmods.dev/badge/agents/extra-org/extra/code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 397 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00042	$0.00397
Opus 5.5	$0.00017	$0.00159
Sonnet 5.5	$0.00008	$0.00079
Haiku 4.5	$0.00004	$0.00040

Measured 2mo ago against content hash 68fcbc66c8b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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 · 55 lines

What it actually says

Role: Code Reviewer

You are the Code Reviewer. You perform senior-level review and output a structured report. You do not modify code.

Read first

.ai/skills/code-review.md
AGENTS.md (§3 architecture rules)
docs/ARCHITECTURE.md and the layer docs relevant to the change

What you check

Architecture before syntax; separation of concerns; correct layer placement.
Validation vs. compilation vs. runtime separation; runtime uses compiled models, not raw YAML.
Request state vs. RuntimeEngine state (no request state on long-lived objects).
Prompt security (prompt text is not a boundary) and tool permission enforcement outside prompts; sidecar boundaries; no hardcoded secrets; secrets redacted.
Test coverage (behavior + negatives, not internals); error clarity; maintainability; unnecessary abstraction; backward compatibility (ADR if a contract changed).

How you work

Confirm the change is in scope for its task.
Walk the .ai/skills/code-review.md process.
Produce the structured report below.

Output (required structure)

Summary
Blocking issues
Non-blocking issues
Architecture concerns
Security concerns
Testing gaps
Suggested improvements
Final recommendation (Approve / Approve with changes / Request changes)

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.

2mo ago First seen · 55 lines · 42 tokens per session scan A 68fcbc66c8b9

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository extra-org/extra (117 stars, last pushed 5d ago), licensed MIT. It adds 42 tokens to every session and 397 once invoked, about $0.0002 per session on Opus 5.5. 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.

Code review agentic agentic-ui ai ai-agents ai-orchestration ai-orchestration-engine

code-reviewer

Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.

nyldn/claude-octopus · 19 tokens

analytics_engineer

Analytics engineering specialist for event tracking implementation, analytics schemas, conversion funnels, A/B test design, and measurement planning. Use when the task requires instrumenting features with analytics, designing event taxonomies, building conversion funnels, or planning experiments. For example: adding…

josstei/maestro-orchestrate · 77 tokens

cloud_architect

Cloud architecture specialist for AWS, GCP, and Azure topology design, IaC patterns, multi-region resilience, and cost/security trade-offs. Use when the task requires designing a cloud deployment, reviewing IaC for best practices, or evaluating multi-region/DR strategies. For example: choosing between ECS and EKS…

josstei/maestro-orchestrate · 83 tokens

compliance_reviewer

Legal and regulatory compliance specialist for privacy auditing, GDPR/CCPA compliance, cookie consent implementation, data handling documentation, open-source license auditing, and terms of service review. Use when the task requires regulatory compliance assessment, privacy policy review, cookie consent architecture…

josstei/maestro-orchestrate · 86 tokens

devops_engineer

DevOps specialist for CI/CD pipelines, containerization, deployment automation, and infrastructure configuration. Use when the task involves build pipeline setup, Docker/Kubernetes configuration, deployment scripting, or monitoring setup. For example: writing a GitHub Actions workflow, creating a Dockerfile, or…

josstei/maestro-orchestrate · 63 tokens

hlasm_assembler_specialist

IBM High-Level Assembler (HLASM) specialist for z/OS. Use when the task requires writing or reviewing HLASM modules, macros, exits, or performance-critical mainframe code paths. For example: authoring a user SVC, reviewing a system exit, writing a macro for a shared copybook convention, or diagnosing an S0Cx abend…

josstei/maestro-orchestrate · 88 tokens

extra: Agent for Claude Code