Algorithm Expert — Development agent for Claude Code
RL algorithm expert.
How to install Algorithm Expert
Installs to ~/.claude/agents/inclusionai-areal-algorithm-expert.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/inclusionAI/AReaL/HEAD/.claude/agents/algorithm-expert.md -o ~/.claude/agents/inclusionai-areal-algorithm-expert.md Restart Claude Code, or start a new session, for it to be picked up.
What Algorithm Expert does
name: algorithm-expert description: RL algorithm expert. Use when dealing with GRPO, PPO, DAPO, reward shaping, advantage normalization, or training loss computation. tools:
- Read
- Grep
- Glob
- Task model: opus
Algorithm Expert
You are an expert in reinforcement learning algorithms for LLM training, specializing in PPO-family algorithms and reward optimization.
When to Activate
Use this agent when:
- Working with GRPO, PPO, DAPO, RLOO, GSPO, or related algorithms
- R
Alternatives in Development
- [Breakthrough Title] — Date: YYYY-MM-DD Tags: #performance #architecture #algorithm (relevant tags) 1.3k ★
- Lex Legal — Use this agent when dealing with legal and compliance activities 523 ★
- Mathodology Coder — Use for reproducible computation, simulation, optimization, figures, tables, and experiment logs 137 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Run Issues Review Gate Critical
Review gate for a /run-issues issue whose diff CHANGES money computation, auth, or secret handling. Same job a
Categorize CSV Agent
Categorize transactions in normalized CSV files based on descriptions. Use after normalization.
Economic Analyst
Owns checklist 06 (economic & logic) and the economic known-vectors — flash loans, first-depositor, MEV, oracl
Cutandrun Pipeline
Execute CUT&RUN pipeline from FASTQ to peaks with Bowtie2, SEACR, and spike-in normalization
Risk Aggressive
tradefloor risk team (analyze and scout runs), aggressive seat. Argues for taking the trade at full size or la
Engagement Critic
Independent reward verifier. Re-reads the vault with fresh context, runs engagement-gate.mjs, and is the ONLY
Related Skills
Nse Trading Skills
9 Claude Code skills for Indian stock trading — technical analysis, position sizing, stop-loss, trailing stops
Post Training
ai-research-skills GRPO, RLHF, DPO, SimPO
Multi Agent Training Grpo
A multi-agent system trained with GRPO for reliable long-horizon task planning and execution.