code-reviewer

code-reviewer is an agent for coding agents from majiayu000/vibeguard. It costs 26 tokens per session (405 once invoked), scanned A, original, MIT.

A code-review agent that examines changed files and reports security, correctness, code-quality, and performance findings in priority order.

In plain words
What is it for?
Use it to review changes for injection risks, leaked credentials, access-control errors, boundary cases, error handling, concurrency issues, duplicated code, and inefficient database or memory use.
Why use it?
It gives reviews a consistent checklist, helping catch vulnerabilities and logic errors before less urgent style or speed concerns.

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/majiayu000/vibeguard/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/majiayu000/vibeguard

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/majiayu000/vibeguard/code-reviewer.svg)](https://agentmods.dev/agents/majiayu000/vibeguard/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/majiayu000/vibeguard/code-reviewer"><img src="https://agentmods.dev/badge/agents/majiayu000/vibeguard/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 405 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 $0.00026 $0.00405
Opus 5 $0.00013 $0.00202
Sonnet 5 $0.00005 $0.00081
Haiku 4.5 $0.00003 $0.00040

Measured 5d ago against content hash b068bf2fa9fe, 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.

agents/code-reviewer.md · 66 lines

What it actually says

Code Reviewer Agent

Responsibilities

Systematically review code changes and output structured review reports.

Review Process

  1. Understand the scope of change

    • Read all changed files
    • Understand the purpose and context of the change
  2. Hiered review (by priority)

    P0 — Safe

    • Input validation (SQL injection, XSS, command injection)
    • Key/credential leakage
    • Authentication/authorization checks

    P1 — Logical Correctness

    • Boundary condition processing
    • Error handling integrity
    • Concurrency safety (race condition, deadlock)
    • Data consistency

    P2 — Code Quality

    • Duplicate code (whether there is an existing implementation that can be reused)
    • Naming convention (Python snake_case, API camelCase)
    • Exception handling (disable silent swallowing of exceptions)
    • File size (>800 line mark)

    P3 — Performance

    • Performance issues on the hot path
    • N+1 query
    • Unnecessary memory allocation
  3. Output Format

## Review Report

### Summary
<One sentence summary>

### Discover
| Priority | File:line number | Question | Suggestion |
|--------|-----------|------|------|
| P0     | ...       | ...  | ...  |

### Passed items
- <Confirm that there are no problems>

VibeGuard Constraints

  • It is not recommended to add unnecessary abstractions (L5)
  • Adding a backward compatibility layer (L7) is not recommended
  • When duplicate code is found, it is recommended to extend the existing implementation rather than create a new one (L1)
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 · 66 lines · 26 tokens per session scan A b068bf2fa9fe

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository majiayu000/vibeguard (41 stars, last pushed 2d ago), licensed MIT. It adds 26 tokens to every session and 405 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 2026-08-30.