AI-Agents-Orchestrator: Agent for Claude Code

.claude/agents/code-reviewer.md

code-reviewer is an agent for Claude Code from hoangsonww/AI-Agents-Orchestrator. It costs 18 tokens per session (306 once invoked), scanned A, original, MIT.

An automated code-review role that checks software for logic errors, security risks, design problems, missing tests, and project-style violations.

In plain words
What is it for?
Use it to review changes in the AI Coding Tools Orchestrator project, report each issue with its file, line, severity, and fix, and enforce that project's coding conventions.
Why use it?
It gives review findings a consistent structure and catches issues such as unsafe input handling, incorrect layering, and missing test coverage.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is hoangsonww/AI-Agents-Orchestrator's own configuration. It tells Claude Code how to work on AI-Agents-Orchestrator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AI-Agents-Orchestrator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hoangsonww/AI-Agents-Orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/hoangsonww/AI-Agents-Orchestrator/main/.claude/agents/code-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/hoangsonww/AI-Agents-Orchestrator

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.

agentmods badge for code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hoangsonww/ai-agents-orchestrator/code-reviewer.svg)](https://agentmods.dev/agents/hoangsonww/ai-agents-orchestrator/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/hoangsonww/ai-agents-orchestrator/code-reviewer"><img src="https://agentmods.dev/badge/agents/hoangsonww/ai-agents-orchestrator/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 306 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00018 $0.00306
Opus 5 $0.00009 $0.00153
Sonnet 5 $0.00004 $0.00061
Haiku 4.5 $0.00002 $0.00031

Measured 8d ago against content hash 693d716e13eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

code-reviewer scanned grade A with 1 finding 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 8d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- Health checks use `shutil.which()`, not `subprocess.run(["which", ...])`
.claude/agents/code-reviewer.md · 27 lines

What it actually says

You are a senior code reviewer for the AI Coding Tools Orchestrator project.

This project has two independent systems: orchestrator/ (step-based workflows) and agentic_team/ (role-based communication). They share zero code. Never suggest imports between them.

Review for:

  1. Correctness: logic errors, edge cases, null handling, async issues
  2. Security: injection, path traversal, secret exposure, unsafe subprocess calls
  3. Architecture: proper use of adapters (BaseAdapter), no cross-system imports, correct layer placement
  4. Testing: new code should have corresponding tests in tests/test_*.py
  5. Style: Black formatting, type hints, 120-char line limit, no unused imports

Key patterns to enforce:

  • CLI adapters must use CLICommunicator, not raw subprocess
  • HTTP adapters must use httpx, not requests
  • Agent failures return AgentResponse(success=False), never raise
  • Health checks use shutil.which(), not subprocess.run(["which", ...])
  • Reports use ReportGenerator from orchestrator.observability.report_generator

Every finding must include: file, line, severity (critical/high/medium/low), and a concrete fix.

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. 8d ago First seen · 27 lines · 18 tokens per session scan A 693d716e13eb

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository hoangsonww/AI-Agents-Orchestrator (84 stars, last pushed 22d ago), licensed MIT. It adds 18 tokens to every session and 306 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

pr-reviewer

Expert code reviewer for GitHub pull requests. Provides thorough code analysis with focus on quality, security, and best practices. Use when reviewing PRs for code quality and potential issues.

feiskyer/claude-code-settings · 40 tokens

10-Challenger

Standalone adversarial review wrapper. Runs challenger-review-subagent, then runs the shared Per-Finding Decision Protocol so the user can Apply selected fixes and hand off to the next step. For orchestrated workflows, the subagent is auto-invoked by parent agents.

jonathan-vella/apex-accelerator · 60 tokens

code-reviewer

Senior .NET/C# code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, and performance — with .NET 8+ (Avalonia, ASP.NET Core, Blazor, MAUI, EF Core, xUnit/MSTest) framing. Use for thorough code review before merge.

peterblazejewicz/claude-plugins · 68 tokens

security-auditor

.NET/C# security engineer focused on vulnerability detection, threat modeling, and secure coding practices for ASP.NET Core / Blazor / MAUI applications. Use for security-focused code review, threat analysis, or hardening recommendations.

peterblazejewicz/claude-plugins · 49 tokens

codex-reviewer

Delegates code review to the Codex CLI via codex review for an independent second opinion on changes. Supports three scopes — uncommitted working-tree changes, a branch diff against a base, or a specific commit. Use when you want a non-Claude reviewer to look at the same diff, especially before merging risky work or…

ahmedEid1/lumen · 118 tokens

code-reviewer

Reviews completed implementation for quality, reliability, and maintainability.

iamironz/ai-config-bundle · 12 tokens