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/commands/gen-commit-msg.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/commands/areal-project/areal/gen-commit-msg)<a href="https://agentmods.dev/commands/areal-project/areal/gen-commit-msg"><img src="https://agentmods.dev/badge/commands/areal-project/areal/gen-commit-msg/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/commands/areal-project/areal/gen-commit-msg"><img src="https://agentmods.dev/badge/commands/areal-project/areal/gen-commit-msg.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 | $0.00022 | $0.00877 |
| Opus 5.5 | $0.00009 | $0.00351 |
| Sonnet 5.5 | $0.00004 | $0.00175 |
| Haiku 4.5 | $0.00002 | $0.00088 |
Grade A, and why
gen-commit-msg 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Commit Message
Generate a well-formatted commit message based on staged changes.
Usage
/gen-commit-msg [--amend] [--scope <scope>]
Arguments:
--amend: Amend the previous commit instead of creating new--scope <scope>: Force a specific scope (e.g.,workflow,engine)
Workflow
Step 1: Analyze Changes
# Check staged files
git diff --cached --name-only
# Check staged content
git diff --cached
# Check recent commit style
git log --oneline -5
Step 2: Categorize Changes
| Type | When to Use |
|---|---|
feat |
New feature or capability |
fix |
Bug fix |
docs |
Documentation only |
gov |
Governance or maintainer changes |
style |
Formatting/style-only changes |
refactor |
Code change without feature/fix |
perf |
Performance improvement |
test |
Adding or fixing tests |
build |
Build system or dependencies |
ci |
CI pipeline or workflow changes |
chore |
Build, deps, config changes |
revert |
Revert a previous commit |
Step 3: Determine Scope
Infer scope from changed files:
areal/workflow/→workflowareal/engine/→engineareal/reward/→rewardareal/dataset/→datasetareal/api/→apidocs/→docs- Multiple areas → omit scope or use broader term
Step 4: Generate Message
Format:
<type>(<scope>): <subject>
<body>
[Optional sections:]
Key changes:
- change 1
- change 2
Refs: #123, #456
Rules:
- Subject: imperative mood, ~50-72 chars, no period
- Body: explain "why" not "what", wrap at 72 chars
- Key changes: bullet list of main modifications (for complex commits)
- Refs: reference issues/PRs if applicable
Step 5: Confirm and Commit
Show preview:
─────────────────────────────────────
feat(workflow): add vision support to RLVR
Add VisionRLVRWorkflow for vision-language RL training.
Supports image inputs alongside text prompts.
─────────────────────────────────────
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 · 171 lines · 22 tokens per session scan A 9f2e91142141
gen-commit-msg is a command published in the GitHub repository areal-project/AReaL (5,888 stars, last pushed today), licensed Apache-2.0. It adds 22 tokens to every session and 877 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 commands, from other repositories
caveman-commit
Generate a terse caveman-style commit message for staged changes.
commit
Creates commits with Conventional Commits format (feat/fix/docs/refactor/test/chore), scope detection, co-author attribution, and pre-commit hook compliance. Validates staged changes and prevents secrets or generated-only files from being committed. Use for requests to commit, stage and commit, save progress, or write…
quick-push
Git add all, commit with Claude, and push to current/new feature branch.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
dev
Developer tools — debug, commit, PR, code review, refactoring.
careful
Blocks destructive shell commands once invoked: a PreToolUse Bash guard denies rm -rf outside temp dirs, force pushes and remote branch deletes, git reset --hard, DROP TABLE / DROP DATABASE / TRUNCATE, kubectl delete and terraform or tofu destroy, including inside ssh remote commands, and makes Claude ask the…