Gym: Skill for Codex

.agents/skills/nemo-gym-blade-analysis/SKILL.md

nemo-gym-blade-analysis is a skill for Codex from NVIDIA-NeMo/Gym. It costs 106 tokens per session (1,713 once invoked), scanned A, original, Apache-2.0.

A guide for analysing NeMo Gym benchmark rollouts, which are recorded model attempts used to measure performance. It supports BLADE-style reports, benchmark comparisons, and checks for report readiness.

In plain words
What is it for?
Use it to calculate aggregate metrics, compare model runs, inspect rollout evidence, write methodology notes, recommend benchmark improvements, and validate BLADE deliverables.
Why use it?
It turns raw rollout results into structured evidence and helps explain performance changes or failed benchmark reports.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents).

This is NVIDIA-NeMo/Gym's own configuration. It tells 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 · 1,183 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-blade-analysis/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/NVIDIA-NeMo/Gym

Made for: 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-blade-analysis

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/nvidia-nemo/gym/nemo-gym-blade-analysis"><img src="https://agentmods.dev/badge/skills/nvidia-nemo/gym/nemo-gym-blade-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,713 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00106 $0.01713
Opus 5 $0.00053 $0.00856
Sonnet 5 $0.00021 $0.00343
Haiku 4.5 $0.00011 $0.00171

Measured 12d ago against content hash a7ead8dca30c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

nemo-gym-blade-analysis 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/blade_toolkit.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.

.agents/skills/nemo-gym-blade-analysis/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NeMo Gym BLADE Analysis

Invocation Check

Use this skill when the user wants to turn NeMo Gym rollout outputs into an analysis report, benchmark card, model comparison, benchmark-improvement recommendation, or BLADE-ready benchmark package.

Load references/blade-benchmark-build-guide.md when the user asks how to build, validate, submit, or review a BLADE benchmark or asks whether a benchmark has all required BLADE deliverables.

Use the bundled public helper at scripts/blade_toolkit.py for package validation, draft anchor-fact extraction, shallow baseline generation, and local calibration when external BLADE tooling is not available in the target repository.

Do not load benchmark-specific examples by default. Load references/cvdp-report-example.md only when the user explicitly asks for a CVDP example, the original CVDP report layout, or this optional reference, or when the agent is confused about the goal and needs one concrete example to re-anchor on what a BLADE-style report is supposed to look like.

Nemotron-only golden analysis artifacts are available under references/nemotron-analysis-artifacts/ as original-CVDP example artifacts. Load them only when the user explicitly asks to study an example completed BLADE-style report, asks for CVDP artifacts, or the agent is confused about the goal and needs a concrete completed example. Do not load those files by default.

Inputs To Gather

Start by identifying the artifact set:

  • rollout JSONL from ng_collect_rollouts
  • aggregate metrics JSON, if present
  • reward profile JSONL from ng_reward_profile, if present
  • benchmark-specific report directory, if present
  • optional golden analysis artifacts, if the user asks to compare against a curated report
  • config paths, agent name, model name, repeat count, and sampling settings
  • source dataset metadata, license, and known redaction limits

If artifacts are missing, state which claims cannot be supported rather than filling gaps from memory.

If the task is benchmark construction rather than report analysis, first build an inventory of BLADE deliverables: analysis skill, rollout data, and golden report packages with metrics and anchor facts. Current BLADE scoring is handled by the universal blade-judge; benchmark-local judge utilities are optional pre-checks, not required deliverables. Missing deliverables are blocking work items, not footnotes.

Read the full file on GitHub · 183 lines

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. 12d ago First seen · 183 lines · 106 tokens per session scan A a7ead8dca30c

Subscribe to this mod's changes

nemo-gym-blade-analysis is a skill published in the GitHub repository NVIDIA-NeMo/Gym (1,183 stars, last pushed today), licensed Apache-2.0. It adds 106 tokens to every session and 1,713 once invoked, about $0.0005 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

dfam-check

Measure mesh files against Design for Additive Manufacturing (DfAM) rules and report printability findings per process (FDM, SLS, SLA/DLP, metal PBF, MJF). Use when the user asks whether a part is printable, wants overhang/wall-thickness/support analysis of an .stl, .obj, .ply, or .3mf mesh, wants a build-orientation…

earthtojake/text-to-cad · 111 tokens

tooluniverse-phylogenetics

Phylogenetic analysis — de novo multiple sequence alignment (Clustal Omega/MUSCLE/MAFFT via EBImsaalign) and neighbour-joining/UPGMA tree building (EBIbuildphylogenetictree) from your own sequences, plus tree analysis, treeness, saturation (PhyKIT), parsimony-informative sites, alignment gap analysis, DVMC…

mims-harvard/ToolUniverse · 155 tokens

tooluniverse-gene-enrichment

Gene-set enrichment analysis — GO (Biological Process, Molecular Function, Cellular Component), KEGG, Reactome pathway enrichment via clusterProfiler, gseapy, ORA, GSEA. Use for interpreting DEG lists, screen hit lists, or any gene-list-to-pathways query. Includes simplify-cutoff handling and union-vs-total…

mims-harvard/ToolUniverse · 82 tokens

tooluniverse-pharmacogenomics

Pharmacogenomics (PGx) research — drug-gene interactions (CPIC, PharmGKB), CPIC dosing guidelines, variant-drug-response associations, ethnic-allele-frequency considerations, and metabolizer-status scoring. Use for PGx-informed dosing recommendations, CYP/HLA pharmacogenomic allele interpretation, and…

mims-harvard/ToolUniverse · 80 tokens

tooluniverse-population-genetics

Population genetics analysis — allele frequencies (gnomAD, 1000 Genomes), Hardy-Weinberg equilibrium testing, Fst between populations, GWAS associations, evolutionary constraint scores. Use for cross-population variant comparison, ancestry-aware allele frequency lookups, and population-level evolutionary analysis.

mims-harvard/ToolUniverse · 66 tokens

tooluniverse-variant-analysis

VCF and variant analysis — parsing, annotation, classification (synonymous, missense, frameshift, stopgained), VAF filtering, coding vs non-coding categorization, multi-condition variant comparison. Use for VCF parsing, variant fraction calculations (denominator = coding subset only, NOT all variants), and per-sample…

mims-harvard/ToolUniverse · 77 tokens