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 agentmods add skills/nvidia/nemoclaw/nemoclaw-maintainer-refactor-docsnpx skills add NVIDIA/NemoClaw --skill nemoclaw-maintainer-refactor-docsgit clone --depth 1 https://github.com/NVIDIA/NemoClawWhat 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 | $0.00162 | $0.02974 |
| Opus 5 | $0.00081 | $0.01487 |
| Sonnet 5 | $0.00032 | $0.00595 |
| Haiku 4.5 | $0.00016 | $0.00297 |
Grade A, and why
nemoclaw-maintainer-refactor-docs 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 yesterday.
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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactor NemoClaw Documentation
Refactor a bounded documentation section without changing product meaning. Improve findability while preserving every useful fact, one canonical owner per topic, and every supported published route.
Prerequisites
- Work from the NemoClaw repository root.
- Follow the shared Documentation Writing and Review contract before planning or editing.
- Read the full target pages, their navigation entries in
docs/index.yml, their redirects infern/docs.yml, and their inbound links before editing.
Choose the Deliverable
- Treat cross-section ownership, navigation hierarchy, and published URL changes as maintainer-owned decisions.
- For a request to plan, audit, or propose a structure, stop after the information architecture, ownership map, and URL migration plan.
- For a request to refactor, implement the plan, validate it, and report the completed migration.
- Keep the work bounded to the named docs section. Report adjacent debt instead of folding unrelated cleanup into the refactor.
- Allow a cross-section move when canonical ownership requires it, but identify the move explicitly in the plan and migration report.
- Surface a choice only when it changes topic ownership, public URLs, supported variants, or user workflow. Use established repository conventions for routine details.
Step 1: Inventory Before Editing
Read the complete section rather than sampling the longest page.
- List every page and nested group for every OpenClaw, Hermes, and Deep Agents navigation variant.
- List every H2 and H3 in the source pages, then map meaningful prose blocks, tables, callouts, and provider-specific procedures that do not have their own heading.
- Find inbound links, old route and anchor references, redirects, release-note links, README links, tests, generated-page mappings, source comments, and repository instructions that name the current docs owners.
- Record which variants render each page or block.
- Identify repeated procedures, troubleshooting guidance, reference facts, and related-topic lists.
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.
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.
- yesterday First seen · 238 lines · 162 tokens per session scan A 342f3fac758d
nemoclaw-maintainer-refactor-docs is a skill published in the GitHub repository NVIDIA/NemoClaw (22,320 stars, last pushed yesterday), licensed Apache-2.0. It adds 162 tokens to every session and 2,974 once invoked, about $0.0008 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
app
SKILL（技能）模块是平台的核心功能之一，用于管理和组织可复用的技能资源。每个技能可以包含描述、内容、标签、文件等丰富的信息，支持公开分享和私有管理。.
openclaw-security-checker
基于《OpenClaw 极简安全实践指南》和《安全验证与攻防演练手册》的全面安全检测工具。对 OpenClaw 实例的配置、权限、隔离、网络、日志进行系统化审查，输出可量化的安全评分和修复建议。.
qveris
Discover, inspect, and call third-party API capabilities via the QVeris MCP server, then generate production code that calls the QVeris REST API for tasks like fetching weather data, stock prices, or public datasets. Use when the user needs to find an external API, integrate a web service, connect to a third-party…
qveris-cli
Use QVeris CLI to discover and call third-party API tools. Use when you need to find an external API, integrate a web service, or retrieve live data (prices, weather, news, etc).
pentest-whitebox-code-review
Source code security audit using backward taint analysis, slot type classification, render context verification, and 3-phase parallel review producing an exploitation queue.
pentest-api-deep
Deep OWASP API Security Top 10 testing for REST, GraphQL, gRPC, and WebSocket APIs — BFLA, mass assignment, rate limiting, and unsafe consumption.