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-cut-release-tag/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-cut-release-tag)<a href="https://agentmods.dev/skills/nvidia/nemoclaw/nemoclaw-maintainer-cut-release-tag"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-maintainer-cut-release-tag/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-cut-release-tag"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-maintainer-cut-release-tag.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- 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 | $0.00058 | $0.03022 |
| Opus 5 | $0.00029 | $0.01511 |
| Sonnet 5 | $0.00012 | $0.00604 |
| Haiku 4.5 | $0.00006 | $0.00302 |
Grade A, and why
nemoclaw-maintainer-cut-release-tag 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cut Release Tag
Cut one signed annotated semver tag from a generated plan. Use the release scripts for tag writes. Use Run Maintainer E2E for maintainer-requested workflow dispatches. Do not improvise tag, push, version-bump, or other release-state GitHub writes.
Treat these as separate states:
- Tag can be cut: the release entry and required image checks pass. The maintainer chooses to proceed with the displayed documentation coverage and general E2E state. The release brief records both decisions and contains no unresolved prompts.
- Tag cut: the remote signed tag exists and peels to the planned candidate.
- Post-tag follow-through: after reporting the tag as cut, continue the same task. Monitor
latest, release labels, public documentation, and release images. Draft the Announcement and reportlkgstate.
Hard Rules
- Use the requested version. Generate the plan with
--version vX.Y.Z; never infer a bump. - Tag only the candidate captured in the plan.
- By default, plan
origin/mainwithout an exception. For urgent QA qualification, a maintainer may select a historical ancestor with--candidate <full-sha> --exception <reason>. - Require the release entry for a current-main plan. A historical plan records its explicit release-entry exception in the signed release brief.
- Treat documentation coverage as maintainer context, not a tag gate. Show the coverage point, later commits and PRs, review and check state, changed paths, and open managed docs PRs.
- Record the maintainer's documentation decision in the signed release brief.
- Require applicable GHCR base and managed-image publication evidence.
- Treat E2E as maintainer context, not a tag gate. Show the newest full E2E result and let the maintainer run focused tests, run the full suite, or proceed with the displayed status.
- Record every displayed or requested E2E result and the decision in the release brief, the signed Markdown release record. Record a plain-language exception reason when the status is exceptional or a requested run remains unresolved.
- Pass the final release brief to
release:cutwith--message-file. The file becomes the signed tag annotation; do not maintain another exception record. - Ask the maintainer to paste the plan's full confirmation phrase before cutting.
- Push only the planned semver tag. Never push or move
latestorlkghere. - Report the tag as cut immediately after remote readback. This report is a progress checkpoint, not the final response.
- Continue the same task through post-tag follow-through. Do not make a post-tag result a tag gate.
- Ask before a workflow rerun. Never create a GitHub Discussion.
- Never move, delete, or replace an existing remote semver tag unless the maintainer starts a protected-tag remediation.
- Follow the release-train policy and the shared Git and GitHub Access Hard Stop.
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 Changed · -6 lines 5b1c5521b6c8
- 12d ago First seen · 279 lines · 58 tokens per session scan A 9b8000ba2911
nemoclaw-maintainer-cut-release-tag is a skill published in the GitHub repository NVIDIA/NemoClaw (22,442 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 3,022 once invoked, about $0.0003 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.
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.
merge-wave
Triage N open PRs with sharded test262 results, rank by net pass delta, merge winners, close catastrophes. Use when multiple PRs have completed CI and you want to land a batch.