Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add dralkh/iktinah --skill stable-baselines3git clone --depth 1 https://github.com/dralkh/iktinahWrote 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/dralkh/iktinah/stable-baselines3)<a href="https://agentmods.dev/skills/dralkh/iktinah/stable-baselines3"><img src="https://agentmods.dev/badge/skills/dralkh/iktinah/stable-baselines3/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/dralkh/iktinah/stable-baselines3"><img src="https://agentmods.dev/badge/skills/dralkh/iktinah/stable-baselines3.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 | $0.00087 | $0.02528 |
| Opus 5.5 | $0.00035 | $0.01011 |
| Sonnet 5.5 | $0.00017 | $0.00506 |
| Haiku 4.5 | $0.00009 | $0.00253 |
Grade A, and why
stable-baselines3 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 1mo 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.
This is a copy
89% identical to stable-baselines3 — 129 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stable Baselines3
Overview
Stable Baselines3 (SB3) is a PyTorch-based library providing reliable implementations of reinforcement learning algorithms. This skill provides comprehensive guidance for training RL agents, creating custom environments, implementing callbacks, and optimizing training workflows using SB3's unified API.
Current upstream: SB3 2.8.0 (April 2026). Docs: stable-baselines3.readthedocs.io.
Installation
Tested against stable-baselines3 2.8.0. Requires Python 3.10+ (3.9 dropped in 2.8.0) and PyTorch >= 2.3.
# Basic installation
uv pip install "stable-baselines3>=2.8"
# With extra dependencies (TensorBoard, ale-py for Atari, etc.)
uv pip install "stable-baselines3[extra]>=2.8"
On zsh, quote brackets: uv pip install 'stable-baselines3[extra]>=2.8'.
For MuJoCo continuous-control benchmarks:
uv pip install "gymnasium[mujoco]"
Check your version:
import stable_baselines3
print(stable_baselines3.__version__)
Related Projects
- SB3-Contrib: experimental algorithms (MaskablePPO, CrossQ, QR-DQN, RecurrentPPO) — separate
sb3-contribpackage - RL Baselines3 Zoo: pre-trained agents, hyperparameters, training scripts
- SBX: SB3 + JAX implementations for users who prefer JAX over PyTorch
Core Capabilities
1. Training RL Agents
Basic Training Pattern:
import gymnasium as gym
from stable_baselines3 import PPO
# Create environment
env = gym.make("CartPole-v1")
# Initialize agent (device="cpu" is often faster for MlpPolicy on small envs)
model = PPO("MlpPolicy", env, verbose=1)
# Train the agent
model.learn(total_timesteps=10000)
# Save the model
model.save("ppo_cartpole")
# Load the model (without prior instantiation)
model = PPO.load("ppo_cartpole", env=env)
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 324 lines · 87 tokens per session scan A 5b34f3247224
stable-baselines3 is a skill published in the GitHub repository dralkh/iktinah (77 stars, last pushed 3mo ago), licensed MIT. It adds 87 tokens to every session and 2,528 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to stable-baselines3, differing in 129 lines, and is treated as a copy.
Other skills, from other repositories
hps-academic-paper
A review deck on compositional generalization in large language models — the field map, the gap, the evidence, and open questions. Built as a decision-grade academic research deck for PI, lab group, reviewers.
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.
agent-evolution
A guide to making an AI agent improve from its past runs. It covers how to judge results, extract reusable lessons, and decide whether to store them as knowledge, instructions, code, or model training.
bad-case-to-dpo
A guide to turning failed production agent runs into training and evaluation data. It explains how to find the first mistake, create preference examples for DPO (Direct Preference Optimization), and check that a fix does not damage other tasks.
vector-and-embedding-weaknesses
Hunt vector / embedding weaknesses (OWASP LLM08:2025) — adversarial inputs against the RAG / similarity layer that cause cross-tenant leak, embedding-inversion privacy loss, semantic confusion, and retriever-driven prompt injection.