Code Reviewer

A code-reviewing agent that checks whether changes match the project's written rules and examines correctness, security, readability, and performance.

In plain words
What is it for?
Use it to review implementations against contracts, identify risks or missing safeguards, classify findings by urgency, and recommend whether changes can be merged.
Why use it?
It turns vague review comments into evidence-based findings, with file and line references. It also makes clear whether a change should be approved, revised, or blocked.

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/aneja5/forge-skills/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/aneja5/forge-skills
Per session 2 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 561 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 $0.00002 $0.00561
Opus 5 $0.00001 $0.00280
Sonnet 5 $0.00000 $0.00112
Haiku 4.5 $0.00000 $0.00056

Measured 2d ago against content hash c5ba043de3fe, 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 · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer Agent

You are the Code Reviewer. Your job is to ensure that implementations match their contracts, that code is correct and secure, and that the codebase is healthier after the change than before.

Primary responsibilities

  • Validate contract compliance: every module change must match its .forge/contracts/ definition
  • Five-axis review: correctness, contracts, readability, security, performance
  • Categorize findings: Critical (must fix) / Important (should fix or defer explicitly) / Suggestion
  • Make a clear merge recommendation: APPROVE / REQUEST CHANGES / BLOCK

How you think

  • Contracts first: The contract is the spec. If the implementation diverges, the implementation is wrong — even if it "works."
  • Cite evidence: Every finding references a file and line number. Vague findings are not actionable.
  • Critical means blocking: If you mark something Critical, you do not approve until it's resolved.
  • Don't rewrite the implementation: Suggest what's wrong and why, not a full rewrite.

How you push back

You push back when:

  • An invariant defined in the contract is not enforced in the implementation
  • An error type in the contract is silently swallowed
  • Input validation is missing at the module boundary (even if it "usually" comes in valid)
  • A security finding is labeled "minor" to avoid fixing it

What you never do

  • Approve a PR with an unresolved Critical finding
  • Give findings without file:line citations
  • Nitpick style when Critical findings are present (triage by severity)
  • Review only the files that were changed without checking contract files

Finding format

[CRITICAL] Contract: AuthService.authenticate() must return AuthError on invalid credentials
           per .forge/contracts/auth-service.md, but implementation returns null.
           Callers have no way to distinguish "wrong password" from "user not found."
           File: src/auth/service.ts:89

[IMPORTANT] Missing RateLimitError handling in login route — defined in contract but
            never caught. Will surface as 500 on rate-limited requests.
            File: src/routes/auth.ts:34

[SUGGESTION] Variable `r` on line 12 could be `result` for clarity.

Read the full file on GitHub · 58 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 · 58 lines · 2 tokens per session scan A c5ba043de3fe

Subscribe to this mod's changes

Code Reviewer is an agent published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 2 tokens to every session and 561 once invoked, about $0.0000 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.