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-e2enpx skills add NVIDIA/NemoClaw --skill nemoclaw-maintainer-e2egit 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 | $0.00041 | $0.01514 |
| Opus 5 | $0.00020 | $0.00757 |
| Sonnet 5 | $0.00008 | $0.00303 |
| Haiku 4.5 | $0.00004 | $0.00151 |
Grade A, and why
nemoclaw-maintainer-e2e 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Maintainer E2E
Use .github/workflows/e2e.yaml from trusted main. Do not substitute local live E2E unless the maintainer explicitly requests local execution.
Push runs publish Relevant E2E. Only a full manual run publishes Release qualification. That
aggregate reports the full suite; it does not decide whether a tag can proceed. A generic E2E
request does not authorize Staging Brev Launchable.
Route the Request
- For E2E against a pull request revision, read and follow Manual PR Runs.
- To dispatch ordinary, focused, staging Launchable, or full E2E on
main, read and follow Main Runs and the Launchable boundary below. - For a release decision inspection, use the section below. Do not load a dispatch reference unless the maintainer requests a new run.
Staging Brev Launchable Boundary
Staging Brev Launchable runs only for a trusted manual dispatch against main. Launchable
mode selects only that job. Full mode adds it to the default E2E selection. The trusted workflow
requires repository maintain or admin permission before the job's source checkout.
The job builds the candidate image, deploys the standing Launchable, and verifies all of these results before it succeeds:
- environment access and the booted image;
- the candidate SHA, image-repository SHA, baked checkout with no uncommitted changes, and absence of runtime overrides;
- hosted and sandbox inference through the preinstalled full E2E suite; and
- Brev workspace deletion and confirmed absence.
Staging Brev Launchable reads these credentials from repository Actions secrets:
BREV_API_KEYauthenticates the trusted host-side Brev CLI for workspace operations in the organization identified byBREV_ORG_ID. Candidate code does not receive this API key.NEMOCLAW_IMAGE_DISPATCH_TOKENis exposed asGH_TOKENonly to the trusted host script. It grants Actions read/write access tobrevdev/nemoclaw-imagefor workflow dispatch, run inspection, and artifact download.NVIDIA_INFERENCE_API_KEYis exported into the Brev guest for the full E2E process. Code in the baked candidate checkout can read and use it.
What ships with it
3 files 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 · 139 lines · 41 tokens per session scan A adec2826308a
nemoclaw-maintainer-e2e is a skill published in the GitHub repository NVIDIA/NemoClaw (22,320 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 1,514 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
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.