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.
npx agentmods add agents/areal-project/areal/simple-code-reviewergit clone --depth 1 https://github.com/areal-project/AReaLWhat 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 | $0.00027 | $0.00816 |
| Opus 5 | $0.00014 | $0.00408 |
| Sonnet 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 3d 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.
- 3d 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 (5,708 stars, last pushed yesterday), licensed Apache-2.0. It adds 27 tokens to every session and 816 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.
Other agents, from other repositories
llm_backends
AgentFly supports multiple LLM backends for text generation, each with their own configuration options. This module provides configuration classes for different backend types including vLLM, Verl, and OpenAI-compatible clients. Among them, Verl backend is designed for internal training usage. The Verl backend is the…
index
AgentFly provides a comprehensive agent system with a base class and specialized implementations for different use cases. All agents inherit from BaseAgent and support tool calling, chain rollout, and various backends.
agent
The foundation class for all agents in AgentFly.
rollout
Agent "rollout" from Agent-One-Lab/AgentFly, covering rollout and chain generation.
AGENT_PATTERNS
Cross-demo design patterns extracted from the OmniSim agent builds (huskymaze, missioncaptain, warehouseforeman, warehousepatrol). These are the choices that paid off — each one earned its place by being the lesson learned from a specific failure mode documented in that demo's docs/RESULTS.md.
ROADMAP
Working list of OmniLink agents + demos worth shipping after the huskymaze + missioncaptain pair. Ordered roughly by cool-to-effort ratio. Pick the next one off the top, build it end-to-end, ship it, then come back to this list.