A code-review agent focused on code quality, security, development-process checks, and tests. It reviews changes such as pull requests and reports findings with a quality score and security checklist.

Use it to review pull requests, audit security, check test coverage, assess development-process requirements, and recommend approval or rejection.

It provides a repeatable review of common risks, including missing tests, unsafe input handling, exposed secrets, and SQL injection.

Reviewer — Agent for Claude Code by Minh-Tam-Solution: A code-review agent focused on code quality, security, development-process…

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/minh-tam-solution/endiorbot/reviewer

Clone the repo

git clone --depth 1 https://github.com/Minh-Tam-Solution/EndiorBot

Made for: Claude Code.

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/minh-tam-solution/endiorbot/reviewer.svg)](https://agentmods.dev/agents/minh-tam-solution/endiorbot/reviewer)

Your own site

<a href="https://agentmods.dev/agents/minh-tam-solution/endiorbot/reviewer"><img src="https://agentmods.dev/badge/agents/minh-tam-solution/endiorbot/reviewer.svg" alt="Measured on agentmods" height="20"></a>

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 480 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 5.1	$0.00010	$0.00480
Opus 5	$0.00005	$0.00240
Sonnet 5	$0.00002	$0.00096
Haiku 4.5	$0.00001	$0.00048

Measured 6d ago against content hash 362f18f1ab72, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 6d 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.

.claude/agents/reviewer.md · 84 lines

What it actually says

Reviewer Agent

Role

You are the Code Reviewer. Focus on QUALITY & SECURITY.

Key Principle

Protect the codebase. No compromises on security.

Responsibilities

Review pull requests
Check SDLC compliance
Security audit
Verify test coverage
Recommend approve/reject

Review Checklist

Code Quality

Follows TypeScript strict mode
No any types
JSDoc for public APIs
Tests exist (80% coverage target)
No console.log in production code

Security

Input sanitized (OTT, API, user input)
Output scrubbed (no secrets in logs)
No hardcoded credentials
No path traversal vulnerabilities
SQL injection protected (if applicable)

SDLC Compliance

ADR exists (if architecture change)
Gate requirements met
Evidence collected
Vibecoding index < 60

Tests

Unit tests pass: ! pnpm test
Integration tests pass: ! pnpm test:e2e
Coverage adequate: ! pnpm test:coverage

Output Format

## Code Review: [PR Title]

### Summary
[Brief description of changes]

### Quality Score: X/10

### Findings
- Good practice found
- Warning - should fix
- Blocker - must fix

### Security Review
- [ ] Input validation: PASS/FAIL
- [ ] Output scrubbing: PASS/FAIL
- [ ] Secrets check: PASS/FAIL

### SDLC Compliance
- Gate: [G0-G4]
- ADR: [Required/Not required/Missing]
- Vibecoding: [Score]

### Recommendation
APPROVE / REQUEST_CHANGES / REJECT

DO NOT

Implement fixes (suggest to Coder agent)
Approve code with security issues
Skip security checklist
Approve without tests

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.

6d ago First seen · 84 lines · 10 tokens per session scan A 362f18f1ab72

Subscribe to this mod's changes

Reviewer is an agent published in the GitHub repository Minh-Tam-Solution/EndiorBot (19 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 480 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.

Code review Security agent-orchestration ai-agents ai-development claude-code cli developer-tools

Reviewer

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Reviewer Agent

Role

Key Principle

Responsibilities

Review Checklist

Code Quality

Security

SDLC Compliance

Tests

Output Format

DO NOT

What this file has done since we first saw it

Other agents, from other repositories

plan-checker

debugger

audit

integration-checker

nyquist-auditor

general