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 nebius/nebius-physical-ai --skill contributionsgit clone --depth 1 https://github.com/nebius/nebius-physical-aiWrote 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/nebius/nebius-physical-ai/contributions)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/contributions"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/contributions/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/nebius/nebius-physical-ai/contributions"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/contributions.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 | $0.00029 | $0.00734 |
| Opus 5 | $0.00015 | $0.00367 |
| Sonnet 5 | $0.00006 | $0.00147 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
contributions 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contributions
Apply these rules to new and changed code when implementing or reviewing an NPA contribution. Keep the change scoped to the requested behavior; existing violations elsewhere are not a reason for a repository-wide rewrite.
Read AGENTS.md, applicable nested instructions, and CONTRIBUTING.md before
editing. Use skills/index.yaml to load the relevant tool or workflow skill.
This skill defines contribution quality; it does not authorize unrelated
operations or publication.
Readability and code style
- Keep functions under 40 lines. Extract named helpers when a function would reach 40 lines or more.
- Name things after domain concepts, not types:
retryBudget, notintValue2. Follow the language's existing casing convention, such asretry_budgetin Python. - Avoid clever one-liners. Prefer three obvious statements over one dense expression.
- Do not abbreviate names except for widely known terms such as
id,url, andhttp. - Comments explain why, never what. Delete comments that restate the code.
- Prefer early returns over nested conditionals. Keep nesting depth at most 3.
Documentation
- Give every exported symbol a docstring with a one-line summary and
Args,Returns, andRaisessections. Use the language's equivalent documentation comment where it has no docstring syntax. StateNonefor inapplicable sections rather than inventing arguments, results, or exceptions. - Start every new module with a header comment stating its responsibility in one sentence. A Python module docstring serves as that header.
- Update the relevant README whenever adding a command, environment variable, or configuration key. Explain what it does, how to use it, and any default or required value; link to detailed reference documentation when needed.
- Write for someone who joined last week and has not read the rest of the repository. Introduce domain concepts and show the context needed to use the changed behavior.
Anti-patterns
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.
- 4d ago First seen · 71 lines · 29 tokens per session scan A c5df394174d7
contributions is a skill published in the GitHub repository nebius/nebius-physical-ai (29 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 734 once invoked, about $0.0001 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 2026-09-07.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…