NVIDIA/NemoClaw is an open-source reference stack for running supported AI agents inside NVIDIA OpenShell sandboxes with managed inference, network policies, integrations, snapshots, and lifecycle controls. It is used to run agents such as OpenClaw, Hermes, and LangChain Deep Agents with administrative and security controls. Catalogue add-ons guide coding agents through NemoClaw workflows.
Borrowing it
Nothing to install: this file belongs to NVIDIA/NemoClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/NVIDIA/NemoClaw/main/.agents/skills/nemoclaw-maintainer-e2e/SKILL.mdgit clone --depth 1 https://github.com/NVIDIA/NemoClawWrote 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/nvidia/nemoclaw/nemoclaw-maintainer-e2e)<a href="https://agentmods.dev/skills/nvidia/nemoclaw/nemoclaw-maintainer-e2e"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-maintainer-e2e/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/nvidia/nemoclaw/nemoclaw-maintainer-e2e"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-maintainer-e2e.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 50 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00037 | $0.00734 |
| Opus 5.5 | $0.00015 | $0.00294 |
| Sonnet 5.5 | $0.00007 | $0.00147 |
| Haiku 4.5 | $0.00004 | $0.00073 |
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 27d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Maintainer E2E
Route the Request
| Request | Procedure |
|---|---|
| Run working-tree source or a selected local commit | Local Runs |
| Run the latest PR commit on GitHub, including failure-triggered comparison with its exact base | Manual PR Runs |
Run the current main commit on GitHub |
Main Runs and the Launchable boundary below |
| Inspect existing evidence for a release decision | Report the Release Context |
| Triage, diagnose, debug, or repair an E2E failure | Load Audit E2E Assertions; this skill still owns dispatch and run-level reporting. |
| Classify one failed GitHub Actions job | For E2E failures, use the assertion-audit route above. For other jobs, load nemoclaw-maintainer-classify-ci-failure. |
A new GitHub candidate run tests the latest PR commit or the current main commit.
Manual PR runs may replay the PR base after a candidate failure, as described in their procedure.
Report arbitrary historical candidate selection as unsupported. Preserve the workflow's identity and trust checks.
Push runs select change-relevant E2E and publish Relevant E2E; they do not always run the full
suite. 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
Exact staging Brev Launchable.
Use .github/workflows/e2e.yaml from trusted main for GitHub runs. Do not substitute local live
E2E unless the maintainer explicitly requests local execution. Do not load a dispatch reference for
a release inspection unless the maintainer requests a new run.
Staging Brev Launchable Boundary
Read Staging Launchable before a dispatch that includes
Exact staging Brev Launchable. It owns the credential, deployment, cleanup, artifact, and queue
boundaries. A generic E2E request does not authorize that job.
What ships with it
6 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.
- 27d ago Changed · +1 lines 1b9905e286ef
- 1mo ago Changed · -86 lines · -12 tokens per session 47c5be4dcb10
- 1mo ago Changed · +1 lines a70781e537aa
- 1mo ago Changed · +9 lines · +8 tokens per session 86f971468986
- 1mo ago Changed · +2 lines 05046f5ed72c
- 2mo ago First seen · 139 lines · 41 tokens per session scan A adec2826308a
nemoclaw-maintainer-e2e is a skill published in the GitHub repository NVIDIA/NemoClaw (22,871 stars, last pushed today), licensed Apache-2.0. It adds 37 tokens to every session and 734 once invoked, about $0.0001 per session on Opus 5.5. 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
github-copilot-upgrader
Use this to update the Github Copilot CLI/SDK.
maintaining-python-tests
Maintains existing pytest and Django test suites without weakening correctness. Use when asked to reduce Python test runtime or CI work, investigate slow pytest families, remove stale migration tests, consolidate repeated setup, improve Python test ownership, or measure whether a test optimization worked after merge.…
agent-starters
Verify every starter supported by the stable production NVIDIA Elements CLI from a fresh consumer environment, investigate failures, and prepare at most one focused repair pull request. Use for nightly or scheduled production starter verification and starter availability failures.
pi-package-sandbox-test
Use when verifying that published Pi packages install and load for normal users, including pi.dev package compatibility checks, release validation, Daytona sandbox tests, and package installability audits.
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.
pentest-business-logic
Business logic vulnerability testing — workflow bypass, payment manipulation, state machine abuse, and function limit circumvention per WSTG-BUSL.