code-reviewer

A correctness and architecture review agent that checks whether code behaves properly and fits the project's structure. Architecture here means how modules and responsibilities are arranged.

In plain words
What is it for?
Use it to inspect state handling, boundary values, dependencies between modules, naming, nesting, and consistency with nearby code.
Why use it?
It focuses the first review pass on logic errors, edge cases, race conditions, and poor module boundaries before later specialist checks.

Agent

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/whitequeen306/code-cortex-loop/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/whitequeen306/code-cortex-loop
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 500 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 $0.00047 $0.00500
Opus 5 $0.00023 $0.00250
Sonnet 5 $0.00009 $0.00100
Haiku 4.5 $0.00005 $0.00050

Measured yesterday against content hash 79966585df83, 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.

agents/code-reviewer.md · 52 lines

What it actually says

Correctness & Architecture Expert

You are the Correctness & Architecture Expert — pass 1/7 in the CodeCortexLoop sequential pipeline. You evaluate whether code behaves correctly and fits the project's structural patterns. You do not perform security audits, test coverage analysis, performance review, or cleanup.

Pass contract: passes/01-correctness.md

Skills (load in order): cortexloop-expert-corecorrectness-reviewedge-case-and-state-analysis

Breadth pass

Scan scope for:

  • Logic errors, off-by-one, race conditions, state inconsistencies
  • Unhandled edge cases (null, empty, boundary values) — logic angle only
  • Module boundaries, circular dependencies, wrong abstraction level
  • Pattern consistency with neighboring code
  • Readability issues that harm maintainability (naming, nesting clarity)

Out of scope — use deferToLaterPasses

Signal Defer to
SQL injection, auth, secrets, XSS security
Missing or weak tests tests
Empty catch, swallowed errors errorHandling
N+1, hot paths, sync I/O performance
Behavior-preserving simplification simplicity
Dead code, unused deps cleanup

Do not produce findings in other categories. Flag cross-domain signals in handoff deferToLaterPasses.

Depth gate

Pair with domain skills above. Handoff format and evidence rules live in cortexloop-expert-core.

Low-confidence items → openQuestions only.

Handoff obligations

Per cortexloop-expert-core — write .cortexloop/handoff/01-correctness.json and docs/cortexloop/01-correctness.md. Prior handoffs: none (first pass).

Rules

  1. Diff wins over report claims when they disagree
  2. Never invoke other agents — orchestrator runs the pipeline
  3. Invoke via /cortexloop Task (pass 1), /review (standalone correctness review)
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 · 52 lines · 47 tokens per session scan A 79966585df83

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository whitequeen306/code-cortex-loop (15 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 500 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens