third-party-eula-preflight

third-party-eula-preflight is a skill for Codex from nebius/nebius-physical-ai. It costs 64 tokens per session (1,461 once invoked), scanned A, original, Apache-2.0.

A checklist for handling third-party end-user licence agreements before downloading or running software, models, images, or datasets. It records which agreements apply and how they must be accepted or declined.

In plain words
What is it for?
Use it before provisioning or submitting workloads that use vendor software, Isaac products, models, data, or other gated resources.
Why use it?
It prevents costly setup from starting with missing licence acceptance and avoids confusing access credentials with permission to use or redistribute something.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it before provisioning or submitting workloads that use vendor software, Isaac products, models, data, or other gated resources.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nebius/nebius-physical-ai/third-party-eula-preflight
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 nebius/nebius-physical-ai --skill third-party-eula-preflight
Clone the repo
git clone --depth 1 https://github.com/nebius/nebius-physical-ai

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 third-party-eula-preflight

README.md
[![agentmods](https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/third-party-eula-preflight/github.svg)](https://agentmods.dev/skills/nebius/nebius-physical-ai/third-party-eula-preflight)
Your own site
<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/third-party-eula-preflight"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/third-party-eula-preflight/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 third-party-eula-preflight

Your own site · 80×15
<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/third-party-eula-preflight"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/third-party-eula-preflight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,461 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 $0.00064 $0.01461
Opus 5 $0.00032 $0.00731
Sonnet 5 $0.00013 $0.00292
Haiku 4.5 $0.00006 $0.00146

Measured 5d ago against content hash 7b9d41103257, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

third-party-eula-preflight 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 5d 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.

skills/atomic/third-party-eula-preflight/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Third-Party EULA Preflight

Run this preflight before any costly or state-changing setup. NPA's Isaac product policy defaults vendor acceptance on for non-interactive workflows while retaining an explicit opt-out. Other third-party agreements remain opt-in unless their product policy documents a default.

Procedure

  1. Inspect the selected image, runtime-fetch/bootstrap path, model and data sources, workflow renderer, and vendor documentation. Name every agreement that governs the exact components the workload will obtain or execute.
  2. Record the vendor's official terms links and documented acceptance mechanism. Do not infer redistribution permission from credentials, registry access, prior use, or acceptance of a different agreement.
  3. Apply the documented product policy. NPA defaults ACCEPT_EULA=Y only for npa-isaac-lab, Isaac-backed SONIC modes, and GR00T Isaac simulation. An absent variable succeeds non-interactively. The affirmative legacy spellings Y, YES, 1, and TRUE are accepted case-insensitively. Empty, N, NO, 0, and FALSE, including --no-accept-eula, opt out and must refuse before download. Any other value is invalid and must fail with an invalid-value error, not be described as an opt-out. Do not reuse this default for unrelated vendor, model, data, privacy, telemetry, or preview terms.
  4. For runtime-fetched Hugging Face weights, do not add an NPA EULA/terms boolean, confirmation flag, empty placeholder, or model-check bypass. The operator's token and its actual upstream permissions are the only local gate for a gated repository. Probe every required repository before provisioning, using exact-revision payload bytes and never repository metadata; public repositories may pass anonymously. A token authenticates a fetch and does not change the artifact's redistribution classification.
  5. For non-interactive Isaac execution, forward the default only to Isaac-backed tasks. If the operator opted out, fail before provisioning and print the exact resume command needed to re-enable acceptance.
  6. Expose only ACCEPT_EULA to users. The pip-runtime launcher derives OMNI_KIT_ACCEPT_EULA=YES internally after validating the public value; do not add duplicate CLI, workflow, or configuration plumbing for it.
  7. Never default optional privacy or telemetry consent. Keep PRIVACY_CONSENT and telemetry off by default; enable them only independently and explicitly, and do not derive either from EULA acceptance.
  8. Keep acceptance UX separate from redistribution classification. A convenient default does not grant redistribution rights; the Isaac-family images remain public because their built layers contain no proprietary Isaac or Kit bytes.
  9. Preserve a redacted run record containing agreement names, official links, the operator-stated scope, preflight result, and resume command. Do not store secret values or unnecessary personal data.

Read the full file on GitHub · 117 lines

Files

What ships with it

1 file 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. 5d ago Changed · +1 lines 7b9d41103257
  2. 9d ago First seen · 116 lines · 64 tokens per session scan A 0e29fd026d66

Subscribe to this mod's changes

third-party-eula-preflight is a skill published in the GitHub repository nebius/nebius-physical-ai (27 stars, last pushed today), licensed Apache-2.0. It adds 64 tokens to every session and 1,461 once invoked, about $0.0003 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

specification-writing

A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.

wanshuiyin/Auto-claude-code-research-in-sleep · 49 tokens

regulatory-research-fallback

Fallback workflow for regulatory research when web extraction tools fail on government PDFs.

HKUDS/OpenSpace · 20 tokens

x-scorecard

OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.

x-cmd/x-cmd · 57 tokens

memstack-business-gdpr

Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…

cwinvestments/memstack · 121 tokens

gesellschaftsrechtliche-satzungen-agb

Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.

Klotzkette/claude-fuer-deutsches-recht · 69 tokens

nda-review

Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…

LegalQuants/lq-ai · 79 tokens