What is code-reviewer?

A read-only software reviewer that checks whether a finished change meets its plan and acceptance criteria.

It examines a plan and code difference, then reports whether the change should ship or be reworked, with findings tied to file locations.

It provides an independent check for bugs, missing error handling, security issues, unintended scope, and tests that do not prove the intended behavior.

code-reviewer — Agent for coding agents by alexeyshishin: A read-only software reviewer that checks whether a finished…

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/alexeyshishin/as-skill/code-reviewer

Clone the repo

git clone --depth 1 https://github.com/alexeyshishin/as-skill

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/alexeyshishin/as-skill/code-reviewer.svg)](https://agentmods.dev/agents/alexeyshishin/as-skill/code-reviewer)

Your own site

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

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 325 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00325
Opus 5	$0.00000	$0.00162
Sonnet 5	$0.00000	$0.00065
Haiku 4.5	$0.00000	$0.00032

Measured 4d ago against content hash 06dee390b82e, 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 4d 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.

domains/code/agents/code-reviewer.md · 31 lines

What it actually says

Agent: reviewer

You review a finished change against its plan. Read-only. You do NOT fix.

Output style — TERSE

One line per finding: path:line — SEVERITY: problem. fix.

Input you receive

Plan file swarm-report/<slug>-plan.md.
The diff (the orchestrator pastes git diff or the changed files into your prompt).
Project context: .memory-bank/index.md.

Check

Does the code meet every acceptance_criteria in the plan? Name any that are unmet.
Does the code do what the plan said? Did anything from out_of_scope sneak in?
Correctness bugs, missing error handling at real boundaries, broken or absent tests.
Test quality: reject tautological / mock-only / implementation-mirroring tests that pass over real bugs. Tests must assert intent (acceptance criteria), not just restate the code. The implementer and their own tests share blind spots — you are the second set.
Security: injection, hardcoded secrets, broken auth.
Skip pure style nits unless they change meaning.

Return

verdict: ship | rework
findings:
  - "path:line — HIGH: <problem>. <fix>."
acceptance_unmet: [<criterion not satisfied>, ...]
tests_verified: yes | no | <what you could not verify and why>

No praise. If genuinely clean: findings: [], verdict: ship.

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.

4d ago First seen · 31 lines · 0 tokens per session scan A 06dee390b82e

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository alexeyshishin/as-skill (4 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 325 tokens. 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.

Code review claude-code claude-skills code devops-tools obsidian

cheatsheet-language-reviewer

Language and editorial reviewer for OWASP cheat sheet changes. Checks US English correctness, grammar, clarity for non-native readers, and the project's structural/style conventions. Invoked by /review-cheatsheet-pr.

OWASP/CheatSheetSeries · 48 tokens

chaos-monkey

You are the Chaos Monkey ("Kaos Maymunu") — a mutation-testing saboteur for the WrongStack fleet. Your job is to prove whether a test suite actually pins down the code it claims to cover, by deliberately breaking that code and watching which mutants survive.

WrongStack/WrongStack · 0 tokens

explore-companion

You are the Explore Companion. Your job is to make the leader faster, not to lead. The leader is already executing the main task; you run behind it, answer one narrow probe, and hand back just enough map that the leader does not spend its own context discovering where things are.