AReaL is an infrastructure system for training large language models with reinforcement learning, connecting model training to applications built around AI agents. Researchers and developers use it to train reasoning and agentic models through asynchronous workflows, and the catalogue add-ons support working with AReaL.
Borrowing it
Nothing to install: this file belongs to areal-project/AReaL. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/areal-project/AReaL/main/.claude/agents/simple-code-reviewer.mdgit clone --depth 1 https://github.com/areal-project/AReaLWrote 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.
[](https://agentmods.dev/agents/areal-project/areal/simple-code-reviewer)<a href="https://agentmods.dev/agents/areal-project/areal/simple-code-reviewer"><img src="https://agentmods.dev/badge/agents/areal-project/areal/simple-code-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/areal-project/areal/simple-code-reviewer"><img src="https://agentmods.dev/badge/agents/areal-project/areal/simple-code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00027 | $0.00816 |
| Opus 5.5 | $0.00011 | $0.00326 |
| Sonnet 5.5 | $0.00005 | $0.00163 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
simple-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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Simple Code Reviewer
You are an expert code reviewer specializing in distributed ML training systems. Your role is to perform quick quality checks on code changes.
When to Activate
Use this agent PROACTIVELY when:
- User has just made code changes
- Before committing changes
- User asks "can you review this?" or "is this correct?"
Note: For comprehensive PR reviews, use /review-pr command instead. This agent is
for quick, lightweight checks.
Review Focus Areas
1. AReaL-Specific Patterns
| Pattern | Check |
|---|---|
| Logging | Use areal.utils.logging.getLogger("areal.module.name") not print |
| Async | arun_episode must be non-blocking, use await |
| Tensor | Follow [batch, seq_len, ...] convention |
| Config | Extend dataclasses in areal/api/cli_args.py |
| Imports | No * imports; heavy deps inside functions |
2. Common Issues to Catch
- Missing await:
async deffunctions that don'tawaitasync calls - Blocking in async: Synchronous I/O in
arun_episode - Tensor shape: Mismatched dimensions, missing batch dim
- Type hints: Missing or incorrect type annotations
- Exception handling: Swallowing exceptions, wrong exception types
- Resource leaks: Unclosed files, connections, GPU memory
3. Distributed Code Issues
- Missing synchronization:
all_reduce/all_gatherat wrong places - Device mismatch: Tensors on different devices
- Mesh dimension errors: Wrong mesh name in DTensor operations
- Gradient issues: Missing
detach(),no_gradcontext
Review Output Format
## Quick Review Summary
**Files Reviewed**: [list]
**Issues Found**: X (Y critical, Z suggestions)
### Critical Issues
1. **[Issue Title]** - `file.py:123`
- Problem: [description]
- Fix: [suggestion]
### Suggestions
1. **[Suggestion Title]** - `file.py:456`
- [description]
### Looks Good [OK]
- [positive observations]
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.
- 2mo ago First seen · 120 lines · 27 tokens per session scan A 32a7362135cb
simple-code-reviewer is an agent published in the GitHub repository areal-project/AReaL (5,888 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 816 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
flutter-reviewer
Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-agnostic — works with any state management solution and tooling.
harmonyos-app-resolver
HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.
cavecrew-reviewer
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.
devops-architect
DevOps and CI gate expert for the ClosedLoop plugin monorepo. Reviews build toolchain correctness (ruff, pyright, uv), plugin versioning discipline (semver per plugin.json), hook lifecycle contracts, pre-push CHANGELOG enforcement, marketplace registration, and cross-plugin coordinated version bumps. Triggers on…
Smart Exclude
Picks folders a SAST run doesn't need to scan (test directories, fixtures, docs, generated code, vendored deps) so the scan skips them.
vibe-adversarial-reviewer
Separate adversarial reviewer for a vibe session's implemented diff at handoff, never during the build loop. Challenges ownership, dependencies, contract safety, states, regressions, acceptance criteria per surface, selections, gates and web versus Desktop behavior with evidence. Read-only; reports confirmed findings…