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 review-checklistgit 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/review-checklist)<a href="https://agentmods.dev/skills/nebius/nebius-physical-ai/review-checklist"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/review-checklist/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/review-checklist"><img src="https://agentmods.dev/badge/skills/nebius/nebius-physical-ai/review-checklist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.00329 |
| Opus 5 | $0.00015 | $0.00164 |
| Sonnet 5 | $0.00006 | $0.00066 |
| Haiku 4.5 | $0.00003 | $0.00033 |
Grade A, and why
review-checklist 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 11d 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.
What it actually says
Review Checklist
Prioritize findings that can break users, expand permissions, hide failures, or make parallel agent runs unsafe.
- API contract safety: are new endpoints backward compatible? Does removing a field break existing callers?
- Silent IAM expansion: any change that quietly adds new IAM permissions is a HIGH finding. It must be explicit and operator-approved.
- Exception handling: bare
except:or overly broadexcept Exception:that discards traceback context is a MEDIUM finding. Prefer typed exceptions withraise ... from e. - Cleanup safety: cleanup code must be best-effort. Use
try/finally; never let cleanup raise and abort the cleanup sequence.also_teardown_controller=Falseis the established safe default for SkyPilot. - Narrow exception paths: test coverage for failure paths such as submit failure, auth failure, and cleanup failure is required. Absence is a MEDIUM finding.
- Concurrent run safety: does the code handle parallel Codex runs safely? Check for file ownership assumptions and missing commit-lock patterns.
- Config injection consistency: config should resolve through one precedence-ordered path: explicit arg, then env var, then config file. Inconsistent resolution is a MEDIUM finding.
- Temp file leaks:
tempfile.mkdtempwithout cleanup on exception paths is a MEDIUM finding. PreferTemporaryDirectorycontext manager. - Version pins: required dependency versions should be asserted at runtime, not just documented.
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.
- 11d ago First seen · 19 lines · 31 tokens per session scan A 735f7f44e287
review-checklist is a skill published in the GitHub repository nebius/nebius-physical-ai (28 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 329 once invoked, about $0.0002 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.
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…