A library for building and training reinforcement-learning systems, where an agent learns by receiving rewards or penalties for its actions. It supports fast training, custom environments, parallel simulations, and multiple agents.

Use it to train reinforcement-learning agents, create custom environments, run parallel simulations, and work with Gymnasium, PettingZoo, Atari, or Procgen environments.

It reduces the engineering work needed to run many learning environments at once. It also provides a path for connecting experiments to existing reinforcement-learning environments.

pufferlib — Skill for Claude Code by jimmc414/Kosmos

Install

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.

Any agent

npx skills add jimmc414/Kosmos --skill pufferlib

Clone the repo

git clone --depth 1 https://github.com/jimmc414/Kosmos

Made for: Claude Code.

Or install scientific-skills, the plugin that ships this one along with the rest of its 119 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jimmc414/kosmos/pufferlib/github.svg)](https://agentmods.dev/skills/jimmc414/kosmos/pufferlib)

Your own site

<a href="https://agentmods.dev/skills/jimmc414/kosmos/pufferlib"><img src="https://agentmods.dev/badge/skills/jimmc414/kosmos/pufferlib/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jimmc414/kosmos/pufferlib"><img src="https://agentmods.dev/badge/skills/jimmc414/kosmos/pufferlib.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,997 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin unknown No closer match found in the catalogue.

Token cost

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	$0.00083	$0.02997
Opus 5.5	$0.00033	$0.01199
Sonnet 5.5	$0.00017	$0.00599
Haiku 4.5	$0.00008	$0.00300

Measured 2mo ago against content hash 2614a6808c5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pufferlib 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/env_template.py, scripts/train_template.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

kosmos-claude-scientific-skills/scientific-skills/pufferlib/SKILL.md · 431 lines

The source is not reproduced here

No licence file

Read it on GitHub

Files

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.

Changes

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 · 431 lines · 83 tokens per session scan A 2614a6808c5a

Subscribe to this mod's changes

pufferlib is a skill published in the GitHub repository jimmc414/Kosmos (605 stars, last pushed 28d ago), with no licence file. It adds 83 tokens to every session and 2,997 once invoked, about $0.0003 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 2026-09-03.

Data and AI Game development

pufferlib next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pufferlibjimmc414/Kosmos	Skill	605	28d ago	none	A	83	Claude Code
cdf-autonomous-vehicle-dataset-generationNVIDIA/skills	Skill	3.9k	yesterday	Apache-2.0	A	66	Claude Code, Codex
pufferlibK-Dense-AI/scientific-agent-skills	Skill	56k	4d ago	MIT	C	68	Claude Code
dart-model-upgradedartsim/dart	Skill	1.2k	yesterday	BSD-2-Clause	A	42	Claude Code
mjlab-to-mjswanttktjmt/mjswan	Skill	364	yesterday	Apache-2.0	A	0	Claude Code
ai-game-world-designnirholas/three.ws	Skill	269	yesterday	Apache-2.0	A	88	Claude Code, Codex
PuerTS Agent Development GuideTencent/puerts	Skill	6.3k	3d ago	none	A	39	Claude Code, Codex