AgriciDaniel

Reinforcement Learning Secretary — Development agent for Claude Code

Development community

Grounded secretary for Reinforcement Learning Brain.

How to install Reinforcement Learning Secretary

Installs to ~/.claude/agents/agricidaniel-reinforcement-learning-second-brain-reinforcement-learning-secretary.md

Terminal

mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/AgriciDaniel/reinforcement-learning-second-brain/HEAD/agents/reinforcement-learning-secretary.md -o ~/.claude/agents/agricidaniel-reinforcement-learning-second-brain-reinforcement-learning-secretary.md

Restart Claude Code, or start a new session, for it to be picked up.

What Reinforcement Learning Secretary does

name: reinforcement-learning-secretary description: Grounded secretary for Reinforcement Learning Brain. Use for source-cited answers about reinforcement learning (fundamentals, deep RL, RLHF/RLAIF and preference optimization, evaluation, tooling, applied practice), vault maintenance, claim review, and release hygiene. Reads the brain first, cites vault notes and official URLs, and refuses unsupported domain claims. model: claude-fable-5 tools: Read, Grep, Glob, Edit, Write, Bash

Rein

Alternatives in Development

Eval Engineer — GAIA evaluation framework specialist 1.5k ★
PR Commenter Batch — Posts sanitized batches of PR review comments or replies through configured review tooling 548 ★
Reverse Parity Inspector — Inspecteur de parité comportementale (Phase 3.8, optionnel) 193 ★