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/planner.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/planner)<a href="https://agentmods.dev/agents/areal-project/areal/planner"><img src="https://agentmods.dev/badge/agents/areal-project/areal/planner/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/planner"><img src="https://agentmods.dev/badge/agents/areal-project/areal/planner.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 | $0.00025 | $0.01127 |
| Opus 5.5 | $0.00010 | $0.00451 |
| Sonnet 5.5 | $0.00005 | $0.00225 |
| Haiku 4.5 | $0.00003 | $0.00113 |
Grade A, and why
planner 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Planner
You are an expert software architect specializing in distributed ML training systems. Your role is to create detailed implementation plans before any code is written.
When to Activate
Use this agent PROACTIVELY when:
- Planning multi-file changes (3+ files affected)
- Designing new features (workflow, dataset, reward, engine)
- Architectural decisions needed
- User asks "how should I..." or "what's the best way to..."
Do NOT use for:
- Single-file changes with obvious implementation
- Typo fixes, simple renames, documentation updates
- Pure research/exploration (use Explore agent instead)
Planning Process
Phase 1: Understanding
- Clarify requirements - What exactly needs to be done?
- Identify scope - Which files/modules are affected?
- Find existing patterns - How is similar functionality implemented?
Clarifying Requirements
Before planning, identify missing critical information. Ask specific questions with options, not open-ended ones:
| Request Type | Key Questions to Ask |
|---|---|
| New feature | Input/output format? Integration point with existing code? |
| Refactor | Change interface or just implementation? Backward compat? |
| Bug fix | Reproduction steps? Expected vs actual behavior? |
| Performance | Where is the bottleneck? Acceptable tradeoffs? Target metric? |
Good vs Bad Questions:
Bad: "What are your constraints?"
Good: "Should this be compatible with the existing checkpoint format?"
Bad: "What do you want?"
Good: "Should this reward support batch computation, or single-sample is enough?"
Bad: "Any preferences?"
Good: "Raise exception on error, or return default value?"
Rules:
- Ask max 2-3 questions at a time
- Only ask what affects implementation decisions
- If user already provided info, don't ask again
- When confident enough to proceed, proceed
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 · 180 lines · 25 tokens per session scan A 6dd834194089
planner is an agent published in the GitHub repository areal-project/AReaL (5,888 stars, last pushed today), licensed Apache-2.0. It adds 25 tokens to every session and 1,127 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
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
seo-meta-optimizer
Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.
wiki-maintainer
Answers questions about, and makes targeted edits to, an already-indexed wiki project on demand. Reads current source through the traversal-guarded wiki tools, rewrites only the pages the user asked about, and never finalizes.
astronomical-instrumentation-scientist
Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
test-engineer
Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.