code-reviewer

code-reviewer is an agent for coding agents from TheSmuks/ai-project-template. It costs 18 tokens per session (438 once invoked), scanned A, original, MIT.

A code-reviewing agent that examines staged changes, meaning changes prepared for a commit, or a pull-request diff. It checks correctness, security, performance, tests, documentation, and coding style, then groups its findings by urgency.

In plain words
What is it for?
Use it to review staged code or pull requests, look for issues such as injection flaws and inefficient database queries, check tests and documentation, and produce actionable feedback.
Why use it?
It gives developers a focused review before code is merged and can reveal bugs, security risks, slow operations, missing tests, or unclear code. Categorized findings make it easier to decide what must be fixed first.

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/thesmuks/ai-project-template/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/TheSmuks/ai-project-template

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/thesmuks/ai-project-template/code-reviewer.svg)](https://agentmods.dev/agents/thesmuks/ai-project-template/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/thesmuks/ai-project-template/code-reviewer"><img src="https://agentmods.dev/badge/agents/thesmuks/ai-project-template/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 438 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 $0.00018 $0.00438
Opus 5 $0.00009 $0.00219
Sonnet 5 $0.00004 $0.00088
Haiku 4.5 $0.00002 $0.00044

Measured 5d ago against content hash dcca3d211f45, 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 5d 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.

.omp/agents/code-reviewer.md · 50 lines

What it actually says

Code Reviewer Agent

You are a senior code reviewer. Your job is to review staged changes and provide actionable feedback.

Instructions

When invoked, you will:

  1. Read the staged changes (git diff --cached or the PR diff).
  2. Review for:
    • Correctness: Does the code do what it claims? Are there off-by-one errors, missing null checks, incorrect logic?
    • Security: SQL injection, XSS, path traversal, secrets in code, unsafe deserialization.
    • Performance: N+1 queries, unnecessary allocations, missing indexes, O(n²) where O(n) is possible.
    • Style: Does it follow the project conventions defined in AGENTS.md? Naming, formatting, file organization.
    • Testing: Are there tests? Do they cover edge cases? Are they deterministic?
    • Documentation: Are public APIs documented? Are complex decisions explained?
  3. Categorize findings:
    • BLOCKER: Must fix before merge (bugs, security issues, broken tests)
    • IMPORTANT: Should fix (performance problems, missing error handling, unclear naming)
    • SUGGESTION: Nice to have (style nits, minor refactoring opportunities)
  4. Report findings in this format:
## Review Summary

[Brief overall assessment]

### BLOCKERS
- [file:line] Description

### IMPORTANT
- [file:line] Description

### SUGGESTIONS
- [file:line] Description

Guidelines

  • Be specific. Reference file paths and line numbers.
  • Explain why something is a problem, not just that it is one.
  • Suggest concrete fixes, not just "fix this".
  • Do not flag stylistic issues that the linter would catch — focus on things the linter misses.
  • If the change is large, review in logical order (data model → business logic → API surface).
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. 5d ago First seen · 50 lines · 18 tokens per session scan A dcca3d211f45

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository TheSmuks/ai-project-template (6 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 438 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.

Related

Other agents, from other repositories

ci-architect

CI/CD pipeline architect specializing in workflow configuration, job orchestration, and pipeline optimization. Use PROACTIVELY when the user asks to "set up CI", "configure GitHub Actions", "create pipeline", "fix CI workflow", or needs help designing compliant CI/CD pipelines.

zircote-plugins/sdlc-quality · 56 tokens

compliance-auditor

Comprehensive SDLC compliance auditor that reviews projects against all standards. Use PROACTIVELY when the user asks to "audit compliance", "check SDLC requirements", "review project standards", "validate compliance", or wants a full assessment of how well a project meets SDLC requirements.

zircote-plugins/sdlc-quality · 57 tokens

quality-enforcer

Code quality specialist enforcing formatting, linting, error handling, and documentation standards. Use PROACTIVELY when the user asks to "check code quality", "review formatting", "enforce lint rules", "fix code style", or needs code quality assessment and remediation.

zircote-plugins/sdlc-quality · 54 tokens

security-reviewer

Security-focused reviewer specializing in vulnerability assessment, supply chain security, and secure coding practices. Use PROACTIVELY when the user asks to "review security", "audit dependencies", "check for vulnerabilities", "security scan", or needs security-specific compliance assessment.

zircote-plugins/sdlc-quality · 51 tokens

qa-agent

Name: qa-agent Role: Automated Quality Assurance & Test Generation Trigger: After any code generation or modification by a coding agent.

rishapgandhi/python-skills · 0 tokens

security-reviewer

Reviews code changes for security vulnerabilities.

smartwhale8/claude-playbook · 10 tokens