code-reviewer-agent

code-reviewer-agent is a skill for Claude Code, Codex from siarhei-belavus/agent-public. It costs 74 tokens per session (2,106 once invoked), scanned A, original, MIT.

A read-only code-review agent that examines a patch, commit, pull request, or uncommitted changes for correctness, regressions, edge cases, maintainability, and missing tests. It reports concrete findings before general commentary.

In plain words
What is it for?
Use it for first-pass reviews, regression scans, checking whether an implementation is correct, or a second review after fixes. It traces changed code through callers and runs focused validation when appropriate.
Why use it?
It helps catch broken behaviour and weak validation that a quick style review might miss, including problems outside the edited function.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Use it for first-pass reviews, regression scans, checking whether an implementation is correct, or a second review after fixes. It traces changed code through callers and runs focused validation when appropriate.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/siarhei-belavus/agent-public/code-reviewer-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.

Any agent
npx skills add siarhei-belavus/agent-public --skill code-reviewer-agent
Clone the repo
git clone --depth 1 https://github.com/siarhei-belavus/agent-public

Made for: Claude Code, Codex.

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-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/code-reviewer-agent/github.svg)](https://agentmods.dev/skills/siarhei-belavus/agent-public/code-reviewer-agent)
Your own site
<a href="https://agentmods.dev/skills/siarhei-belavus/agent-public/code-reviewer-agent"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/code-reviewer-agent/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.

agentmods 80×15 button for code-reviewer-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/siarhei-belavus/agent-public/code-reviewer-agent"><img src="https://agentmods.dev/badge/skills/siarhei-belavus/agent-public/code-reviewer-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,106 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00074 $0.02106
Opus 5 $0.00037 $0.01053
Sonnet 5 $0.00015 $0.00421
Haiku 4.5 $0.00007 $0.00211

Measured 8d ago against content hash 177b4c516fab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

code-reviewer-agent 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 8d 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.

skills/review/code-reviewer-agent/SKILL.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer Agent

Review code in deliberate passes: correctness first, then maintainability and evolution risk. Keep the review findings-first, concrete, and economical. Prioritize bugs, regressions, unsafe assumptions, lifecycle mistakes, and missing validation over style commentary.

Core Workflow

  1. Establish review scope.

    • Identify the exact change set: git diff, touched files, tests added, and any untracked files that are part of the implementation.
    • Read applicable AGENTS.md and DECISIONS.md files before judging the design.
    • Prefer reviewing the real patch over summarizing architecture from memory.
  2. Run a correctness pass.

    • Look for regressions in control flow, state transitions, persistence, side effects, error handling, and public contracts.
    • Trace changed code through its callers and consumers. Do not stop at the edited function if the behavior depends on surrounding control flow, lifecycle, or state transitions.
    • Verify that tests actually prove the claim being made; weak tests are review findings when they miss the risky path.
  3. Run focused validation.

    • Start with the smallest relevant tests or commands that exercise the changed behavior.
    • Expand only as needed for confidence.
    • Record what you actually ran so the user knows the review is grounded.
  4. Run a plan-compliance pass when a plan exists.

    • Compare the implemented change against the agreed plan, not just against the desired outcome.
    • Flag silent deviations, missing amendments, and places where implementation changed design without human approval.
    • Check whether REVIEW_NOTE markers were used appropriately for non-blocking better alternatives.
  5. Run a maintainability pass.

    • Look for duplication, hidden coupling, scattered sources of truth, and logic that will drift if changed in two places.
    • Call out design debt only when it creates a realistic future bug surface or makes the new feature harder to evolve safely.
    • Prefer “this is a maintenance trap because...” over vague style criticism.

Read the full file on GitHub · 212 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 212 lines · 74 tokens per session scan A 177b4c516fab

Subscribe to this mod's changes

code-reviewer-agent is a skill published in the GitHub repository siarhei-belavus/agent-public (2 stars, last pushed 3mo ago), licensed MIT. It adds 74 tokens to every session and 2,106 once invoked, about $0.0004 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.