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/.agents/skills/commit-conventions/SKILL.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/skills/areal-project/areal/commit-conventions)<a href="https://agentmods.dev/skills/areal-project/areal/commit-conventions"><img src="https://agentmods.dev/badge/skills/areal-project/areal/commit-conventions/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/skills/areal-project/areal/commit-conventions"><img src="https://agentmods.dev/badge/skills/areal-project/areal/commit-conventions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 142 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Agent Snooping · line 147 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 148 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00031 | $0.01256 |
| Opus 5.5 | $0.00012 | $0.00502 |
| Sonnet 5.5 | $0.00006 | $0.00251 |
| Haiku 4.5 | $0.00003 | $0.00126 |
Grade A, and why
commit-conventions 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Conventions
Commit message conventions and scope inference rules for the AReaL repository.
When to Use
ALWAYS load this skill when making any git commit in AReaL. This includes:
- Direct commits (
git commit) - Commits during PR creation (
$create-pr//create-pr) - Commits delegated to sub-agents with this skill loaded
- Any agent workflow that produces a commit
Commit Message Format
<type>(<scope>): <subject>
<body>
[Optional sections:]
Key changes:
- change 1
- change 2
Refs: #123, #456
Type Selection
| 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 |
Scope Inference
Infer scope from the primary changed file paths:
| File Path Pattern | Scope |
|---|---|
areal/workflow/ |
workflow |
areal/engine/ |
engine |
areal/reward/ |
reward |
areal/dataset/ |
dataset |
areal/api/ |
api |
areal/utils/ |
utils |
areal/infra/ |
infra |
areal/trainer/ |
trainer |
areal/models/ |
models |
areal/experimental/ |
experimental |
docs/ |
docs |
examples/ |
examples |
AGENTS.md, .agents/, .claude/, .codex/, .opencode/ |
agents |
| Multiple areas | Omit scope or use broader term |
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 · 181 lines · 31 tokens per session scan A d5d764038726
commit-conventions is a skill published in the GitHub repository areal-project/AReaL (5,888 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 1,256 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 skills, from other repositories
caveman-commit
Write a Conventional Commits message compressed to intent only. Use for "write a commit", "commit message", /commit or /caveman-commit.
contextual-commit
Write contextual commits that capture intent, decisions, and constraints alongside code changes. Use when committing code, finishing a task, or when the user asks to commit. Extends Conventional Commits with structured action lines in the commit body that preserve WHY code was written, not just WHAT changed.
resolve-publish
Commit the validated fix and follow local-only, workflow-owned, or direct PR publication.
feature-publish
Commit the feature, write the PR body, publish in the selected mode, and drive the PR.
ci-commit
Only use when the user explicitly invokes this skill by name.
meta-pre-commit-quality-gate
Run three quality gates (ruff + mypy + pytest) in parallel over the staged diff, then arbitrate a single BLOCK/APPROVE verdict. Use before committing changes locally when you want a comprehensive pre-commit gate beyond per-file linting — exactly the same gate set CI enforces.