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/translate-doc-zh.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/translate-doc-zh)<a href="https://agentmods.dev/commands/areal-project/areal/translate-doc-zh"><img src="https://agentmods.dev/badge/commands/areal-project/areal/translate-doc-zh/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/translate-doc-zh"><img src="https://agentmods.dev/badge/commands/areal-project/areal/translate-doc-zh.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 | $0.00024 | $0.00745 |
| Opus 5 | $0.00012 | $0.00373 |
| Sonnet 5 | $0.00005 | $0.00149 |
| Haiku 4.5 | $0.00002 | $0.00075 |
Grade A, and why
translate-doc-zh 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 10d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document Translation (EN → ZH)
Translate English documentation to Chinese for the AReaL project.
Usage
/translate-doc-zh $ARGUMENTS
Arguments ($ARGUMENTS):
- Path to English document (e.g.,
docs/en/tutorial/quickstart.md)
Document to Translate
!if [ -f "$ARGUMENTS" ]; then echo "File: $ARGUMENTS"; echo ""; head -50 "$ARGUMENTS"; else echo "ERROR: File not found: $ARGUMENTS"; echo "Please provide a valid path to an English document in docs/en/"; fi
Workflow
Step 1: Validate the Path
- Check if
$ARGUMENTSexists - Verify it is inside
docs/en/directory and ends with.md - If invalid, inform user and stop
Step 2: Determine Output Path
- Input:
$ARGUMENTS(e.g.,docs/en/tutorial/quickstart.md) - Output: Replace
docs/en/withdocs/zh/(e.g.,docs/zh/tutorial/quickstart.md)
Step 3: Check if Chinese Document Exists
- If
docs/zh/<path>exists → Modification Scenario - If
docs/zh/<path>does NOT exist → Full Translation Scenario
Scenario 1: Modification (Chinese Document Exists)
Use when Chinese document already exists.
Workflow
- Read both English and Chinese documents
- Compare differences to identify:
- New sections in English
- Modified sections in English
- Deleted sections
- Translate only changed parts
- Preserve all other Chinese content unchanged
Translation Rules:
- Preserve English technical terms: FSDP, FSDP2, GRPO, PPO, DAPO, MoE, LLM, RL, RLVR, Claude Code, OpenCode, Megatron, Archon, SGLang, vLLM, PyTorch, HuggingFace, Transformers, etc.
- File paths and code examples remain unchanged
- Professional and rigorous terminology
- Preserve Markdown format, code blocks, tables
Scenario 2: Full Translation (Chinese Document Does NOT Exist)
Use when Chinese document does not exist.
Workflow
- Read the English source document
- Translate entire document to Chinese
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.
- 10d ago First seen · 107 lines · 24 tokens per session scan A 0f5c92b493a6
translate-doc-zh is a command published in the GitHub repository areal-project/AReaL (5,739 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 745 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 commands, from other repositories
pseo-hreflang-audit
Use when: kullanıcı "hreflang audit", "hreflang denetimi", "i18n", "dil versiyonları", "uluslararası SEO", "x-default", "hreflang reciprocity", "tek-yönlü hreflang", "yanlış dil/bölge kodu", "en-UK" der ya da /pseo-hreflang-audit çağırırsa. Also use when: aktif projenin Screaming Frog export'u alındı…
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.
init
Scaffold a new MindBase project (v2 layout). Usage: /mb:init [template] [-- mission ...].
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.
recall
Search past tool-call observations with BM25 ranking to answer "have I seen this before?" before re-deriving a fix or repeating a mistake. Enforces Law 1 (Research Before Executing).
watch
Live-stream swarm events and agent activity in real time.