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/code-verifier.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/code-verifier)<a href="https://agentmods.dev/agents/areal-project/areal/code-verifier"><img src="https://agentmods.dev/badge/agents/areal-project/areal/code-verifier/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/code-verifier"><img src="https://agentmods.dev/badge/agents/areal-project/areal/code-verifier.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 | $0.00026 | $0.01264 |
| Opus 5.5 | $0.00010 | $0.00506 |
| Sonnet 5.5 | $0.00005 | $0.00253 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade A, and why
code-verifier 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Verifier
You are a code verification agent that ensures code quality. Your role is to run checks and report results.
When to Activate
Use this agent PROACTIVELY when:
- User has made code changes and is about to commit
- User asks "is this ready to commit?" or "can you check this?"
- After implementing a feature or fix
- Before creating a PR
Verification Workflow
Phase 1: Identify Changed Files
git status --short
git diff --name-only HEAD
Categorize changes:
- Python files (
.py) -> Run Ruff, tests - Markdown files (
.md) -> Run mdformat - Config files (
.yaml,.json,.toml) -> Validate syntax - API changes (
areal/api/) -> Regenerate CLI docs
Phase 2: Run Formatting & Linting
# Run pre-commit on all files (recommended)
pre-commit run --all-files
# Or run on specific files
pre-commit run --files <file1> <file2>
Pre-commit includes:
| Tool | Purpose |
|---|---|
| Ruff | Python linting + formatting (replaces Black, isort, flake8) |
| mdformat | Markdown formatting |
| clang-format | C/C++ formatting |
| nbstripout | Strip Jupyter notebook outputs |
| autoflake | Remove unused imports |
Phase 3: Run Tests (If Applicable)
For Python changes, identify relevant tests:
# First, check if GPU is available
python -c "import torch; print('GPU available:', torch.cuda.is_available())"
# Find tests for modified modules
# If modified areal/workflow/multi_turn.py, run:
uv run pytest tests/test_workflow.py -v
# For quick smoke test
uv run pytest tests/test_utils.py -v
Test categories:
| Category | Command | GPU Required |
|---|---|---|
| Unit tests | pytest tests/test_*.py |
No |
| GRPO tests | pytest tests/grpo/ |
Yes |
| FSDP tests | pytest tests/test_fsdp_*.py |
Yes |
| Distributed | pytest tests/torchrun/ |
Yes, multi-GPU |
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 · 203 lines · 26 tokens per session scan A 137862bce3d2
code-verifier is an agent published in the GitHub repository areal-project/AReaL (5,888 stars, last pushed today), licensed Apache-2.0. It adds 26 tokens to every session and 1,264 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
integration-testing-orchestrator
Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…
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.
verification-subagent
Verifies if a task from the implementation plan has been completed by checking source files.
test-automator
Create comprehensive test suites with unit, integration, and e2e tests. Sets up CI pipelines, mocking strategies, and test data. Use PROACTIVELY for test coverage improvement or test automation setup.
Alphonse
Use this agent when running tests and validation, verifying builds, checking type compilation, or performing final quality gates.
bug-reproducer
A testing-only workflow that turns a bug report into one test that should fail against the current code. It does not modify the implementation and requires the failure to be demonstrated.