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-day/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-day)<a href="https://agentmods.dev/skills/nvidia/nemoclaw/nemoclaw-maintainer-day"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-maintainer-day/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-day"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-maintainer-day.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk warn
- 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 | $0.00106 | $0.01042 |
| Opus 5 | $0.00053 | $0.00521 |
| Sonnet 5 | $0.00021 | $0.00208 |
| Haiku 4.5 | $0.00011 | $0.00104 |
Grade A, and why
nemoclaw-maintainer-day 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 today.
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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NemoClaw Maintainer Day
Execute one pass of the maintainer loop, prioritizing version-targeted work.
Autonomy: You may push small fixes after required CI and scheduled automated reviews settle for one unchanged latest PR commit. You may approve a PR when all gates pass. Report contributor and approver overlap as an advisory. It does not change merge readiness or require another reviewer. Never merge. Ask the user about merge, product-scope, and architecture decisions. Also ask when contributor intent is unclear.
Treat the recorded latest PR commit as an optimistic publication guard. Immediately before a push, confirm that the remote branch still points to that commit. Stop when another workflow publishes first.
References
- PR review priorities: PR-REVIEW-PRIORITIES.md
- Risky code areas: RISKY-AREAS.md
- State schema: STATE-SCHEMA.md
Step 1: Check Version Progress
node --no-warnings .agents/skills/nemoclaw-maintainer-day/scripts/version-target.ts
node --no-warnings .agents/skills/nemoclaw-maintainer-day/scripts/version-progress.ts <version>
The first script selects the target version. The second lists shipped and open items.
Step 2: Pick One Action
Before reviewing, repairing, approving, integrating, or pushing a PR, complete PR follow-up successfully for one unchanged latest PR commit. This prerequisite does not apply to an item with no PR candidate.
Select the first applicable action for an open item:
- PR ready for approval — CI passes, no conflicts remain, and tests cover the change. Confirm that there is no unresolved correctness or security issue. Follow MERGE-GATE.md.
- PR that needs a small fix — Follow SALVAGE-PR.md.
- Security item — The item touches a risky area. Follow SECURITY-SWEEP.md.
- Test gap — Risky code does not have sufficient tests. Follow TEST-GAPS.md.
- Repeated conflicts — Follow HOTSPOTS.md.
- Work that needs sequencing — The work is too large for one pass. Follow SEQUENCE-WORK.md.
What ships with it
19 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.
- evals/evals.json 3.7 KB
- HOTSPOTS.md 1.5 KB
- MERGE-GATE.md 5.4 KB
- PR-REVIEW-PRIORITIES.md 5.4 KB
- RISKY-AREAS.md 2.6 KB
- SALVAGE-PR.md 3.0 KB
- scripts/check-gates.ts 120 KB runs code
- scripts/handoff-summary.ts 11 KB runs code
- scripts/hotspots.ts 3.9 KB runs code
- scripts/run-trusted-check-gates.sh 1.4 KB runs code
- scripts/shared.ts 6.8 KB runs code
- scripts/state.ts 7.7 KB runs code
- scripts/triage.ts 19 KB runs code
- scripts/version-progress.ts 2.2 KB runs code
- scripts/version-target.ts 4.4 KB runs code
- SECURITY-SWEEP.md 1.8 KB
- SEQUENCE-WORK.md 1.7 KB
- STATE-SCHEMA.md 1.7 KB
- TEST-GAPS.md 2.6 KB
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.
- today Changed 6fd2908437b1
- 7d ago Changed · +9 lines c98d0c8f71d0
- 11d ago First seen · 94 lines · 106 tokens per session scan A ad36eba79f89
nemoclaw-maintainer-day is a skill published in the GitHub repository NVIDIA/NemoClaw (22,427 stars, last pushed today), licensed Apache-2.0. It adds 106 tokens to every session and 1,042 once invoked, about $0.0005 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
github-copilot-upgrader
Use this to update the Github Copilot CLI/SDK.
dev-workflow
The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.
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.…
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.
slate-ar-ship
Slate v2 one-command ship/readiness mini-skill. Runs finalization preview, picks the review shape, runs pre-commit gates/autoreview, pauses for commit approval, then commits/finalizes after confirmation.
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.