Gym: Skill for Claude Code

.agents/skills/nemo-gym-release-notes/SKILL.md

nemo-gym-release-notes is a skill for Claude Code, Codex from NVIDIA-NeMo/Gym. It costs 50 tokens per session (1,077 once invoked), scanned A, original, Apache-2.0.

A release-notes and README-news writing workflow for NeMo Gym, a software project. It uses the exact changes in a defined release range to explain what users can do and what changed.

In plain words
What is it for?
Use it to draft, edit, prioritise, and validate release notes, changelog highlights, release announcements, and condensed README news entries.
Why use it?
It keeps release summaries tied to shipped commits and pull requests instead of assumptions or changes from other branches. It also checks drafts for duplication, weak priorities, and unsupported claims.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is NVIDIA-NeMo/Gym's own configuration. It tells Claude Code and Codex how to work on Gym itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Gym configures →

About the project

NVIDIA-NeMo/Gym is a library and infrastructure for evaluating and improving models and agents inside environments, where each environment defines tasks, agent interaction, verification, and execution state. It is for teams running reproducible evaluations or training at scale across settings such as code execution, tool calling, and sandboxes, and the catalogue entries provide skills and instructions for working with it.

NVIDIA-NeMo/Gym · 1,320 stars · on GitHub · docs.nvidia.com

Reuse

Borrowing it

Nothing to install: this file belongs to NVIDIA-NeMo/Gym. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/NVIDIA-NeMo/Gym/main/.agents/skills/nemo-gym-release-notes/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/NVIDIA-NeMo/Gym

Made for: Claude Code, Codex.

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.

agentmods badge for nemo-gym-release-notes

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia-nemo/gym/nemo-gym-release-notes/github.svg)](https://agentmods.dev/skills/nvidia-nemo/gym/nemo-gym-release-notes)
Your own site
<a href="https://agentmods.dev/skills/nvidia-nemo/gym/nemo-gym-release-notes"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/gym/nemo-gym-release-notes/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.

agentmods 80×15 button for nemo-gym-release-notes

Your own site · 80×15
<a href="https://agentmods.dev/skills/nvidia-nemo/gym/nemo-gym-release-notes"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/gym/nemo-gym-release-notes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,077 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 original 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.01077
Opus 5.5 $0.00020 $0.00431
Sonnet 5.5 $0.00010 $0.00215
Haiku 4.5 $0.00005 $0.00108

Measured 1mo ago against content hash 519602ea9596, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nemo-gym-release-notes 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.

.agents/skills/nemo-gym-release-notes/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NeMo Gym Release Notes

Write concise release notes that explain what users can now accomplish and why it matters.

Build an evidence base

  1. Identify the previous release tag and exact release branch or commit.
  2. Treat that bounded range as authoritative. Exclude changes outside it, regardless of branch.
  3. Read the preceding release notes for structure, voice, bullet length, punctuation, and emphasis.
  4. For each candidate, record the supporting commit or PR, user outcome, shipped scope, and intended section.
  5. Verify contributor counts and first-time status from the same range, excluding bots.
  6. Check ambiguous claims against the implementing PR, code, tests, and docs.
  7. Distinguish a PR's motivating use case from the interface contract actually shipped.

Work in dependency order

  1. Draft all detailed release-note sections.
  2. Self-review every bullet with the checklist below, then reread the full draft for duplication, inconsistent terminology, misplaced items, weak priority, and contradictions.
  3. Recheck corrected claims against the evidence base.
  4. Derive the Release Summary and Highlights from the approved sections.
  5. Update README news last as a condensed mirror of the approved Highlights.

Write for users

  • Lead with the outcome; name the mechanism afterward.
  • Replace implementation jargon with the task it enables, or define the term on first use.
  • Omit command syntax unless it is essential to the user action; leave procedural details to the documentation.
  • Explain unfamiliar environments or integrations instead of listing names alone.
  • Give migrations enough context for users to understand what changed, whether they are affected, and what action to take.
  • State safety or isolation limits explicitly. For example, host-process execution is not sandbox isolation.
  • Describe only shipped support. Distinguish infrastructure for defining a capability from ready-made implementations, and provider-neutral architecture from providers that implement it.
  • Keep documentation additions in a documentation section rather than presenting them as product capabilities.

Read the full file on GitHub · 97 lines

Files

What ships with it

2 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.

  1. 1mo ago First seen · 97 lines · 50 tokens per session scan A 519602ea9596

Subscribe to this mod's changes

nemo-gym-release-notes is a skill published in the GitHub repository NVIDIA-NeMo/Gym (1,320 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 1,077 once invoked, about $0.0002 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 2026-10-08.

Related

nemo-gym-release-notes compared with skills from other repositories

nemo-gym-release-notes next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
nemo-gym-release-notesNVIDIA-NeMo/GymSkill1.3ktodayApache-2.0A50Claude Code, Codex
model_finetuningvuralserhat86/antigravity-agentic-skillsSkill4310mo agononeA67Claude Code, Codex
model_finetuningDonggangChen/antigravity-agentic-skillsSkill210mo agononeA67Claude Code, Codex
foundry-config-setupmicrosoft/agent-frameworkSkill15kyesterdayMITA65Claude Code, Codex
rowboat-spacesrowboatlabs/rowboatSkill18kyesterdayApache-2.0A60Claude Code, Codex
create-tech-designhumanlayer/humanlayerSkill13kyesterdayApache-2.0A16Claude Code, Codex
deploy-docker-composeomnigent-ai/omnigentSkill11ktodayApache-2.0A84Claude Code, Codex