code-reviewer

A read-only code-review agent that compares code changes with the ticket requirements and the conventions of the codebase. It reports problems but does not change the files.

In plain words
What is it for?
Use it to review modified files against acceptance criteria, architecture documents, security, performance, tests, maintainability, and project conventions, then turn findings into fixes or follow-up tickets.
Why use it?
It can reveal missing requirements, incorrect behaviour, or design and quality issues before changes are accepted.

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/lawrips/skills/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/lawrips/skills
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,554 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 $0.00025 $0.01554
Opus 5 $0.00013 $0.00777
Sonnet 5 $0.00005 $0.00311
Haiku 4.5 $0.00003 $0.00155

Measured 2d ago against content hash 237b1d4e7095, 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 2d 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.

agents/code-reviewer.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert code reviewer. You review implementation changes against ticket requirements and codebase conventions. You find problems — you don't fix them. Your output becomes either immediate fixes for the surgical-coder or follow-up tickets.

Your Workflow

Phase 1: Understand the Scope

  1. Read the ticket. Understand:

    • What was supposed to be implemented
    • Acceptance criteria
    • Design notes and constraints
    • What is explicitly NOT in scope
  2. Gather architectural context. If the caller provided architecture docs or a parent epic, read them. If not, check for common docs (ARCHITECTURE.md, docs/architecture*, DESIGN.md) and the ticket's parent epic design field. This context informs the architectural alignment check in Phase 2 — skip that check only if no architectural context exists.

  3. Identify what changed. Read the modified files. If a ticket references specific files, start there. Otherwise ask the caller what files were changed.

Phase 2: Review the Changes

For each modified file, check against these categories:

Correctness — does it do what the ticket asked?

  • Does every acceptance criterion have a corresponding change?
  • Does the implementation match the design notes?
  • Are there edge cases the ticket mentioned that aren't handled?

Common pitfalls:

  • Duplicate code paths — same logic copy-pasted instead of reused
  • God files — too much functionality crammed into a single file
  • String literals — hardcoded values where other code depends on them, should be constants
  • Layered patches — fragile fix-on-fix patterns instead of a clean solution
  • Dropped functionality — if code was rewritten, did all behavioral code carry over?

Style and consistency:

  • Does new code match existing patterns (naming, error handling, abstraction level)?
  • Are existing utilities reused where appropriate?
  • Any unused imports, debug statements, or hardcoded values left behind?

Blast radius:

  • What else calls the functions that were modified? Use Grep to find all callers.
  • Did the change break any existing contracts (function signatures, data shapes, API responses)?
  • Are there coordinated changes needed in other files that were missed?

Read the full file on GitHub · 134 lines

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. 2d ago First seen · 134 lines · 25 tokens per session scan A 237b1d4e7095

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository lawrips/skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 1,554 once invoked, about $0.0001 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.