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-contributor-create-pr/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-contributor-create-pr)<a href="https://agentmods.dev/skills/nvidia/nemoclaw/nemoclaw-contributor-create-pr"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-contributor-create-pr/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-contributor-create-pr"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-contributor-create-pr.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 | $0.00073 | $0.03663 |
| Opus 5 | $0.00036 | $0.01832 |
| Sonnet 5 | $0.00015 | $0.00733 |
| Haiku 4.5 | $0.00007 | $0.00366 |
Grade A, and why
nemoclaw-contributor-create-pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create GitHub Pull Request
Publish one complete candidate from a feature branch based on the current canonical comparison ref. Treat each pushed commit as one candidate. Finish required CI and scheduled automated reviews before another push. Stop unless branch state, implementation-owned validation, DCO declaration, and GitHub commit verification are complete. For access errors, follow Git and GitHub Access Hard Stop.
Satisfy publication requirements
Branch state
Read the canonical base SHA from GitHub. Fetch the canonical branch into the comparison ref. Confirm that both sources resolve to the same SHA. Then confirm a feature branch, commits to publish, and a clean tree:
nemoclaw_trusted_base_sha="$(gh api --method GET repos/NVIDIA/NemoClaw/git/ref/heads/main --jq '.object.sha')"
test -n "$nemoclaw_trusted_base_sha"
git fetch --no-tags https://github.com/NVIDIA/NemoClaw.git +refs/heads/main:refs/remotes/origin/main
nemoclaw_fetched_base_sha="$(git rev-parse --verify refs/remotes/origin/main)"
test "$nemoclaw_fetched_base_sha" = "$nemoclaw_trusted_base_sha"
git branch --show-current
git log origin/main..HEAD --oneline
git status --short
Every command must succeed. The origin/main name is a local comparison ref; it does not prove remote identity. Do not replace the canonical API endpoint or fetch URL with a checkout remote. Stop if the sources differ. Do not validate against a stale ref. Do not publish from main or with uncommitted changes.
This fetch refreshes read-only comparison evidence. It does not authorize merging or rebasing
main into the candidate. Follow Integrate the base branch
before changing candidate history.
Validation
Normal pre-commit, commit-msg, and pre-push hooks provide early feedback, but a successful commit or push does not prove that they ran; hooks can be missing, stale, or redirected through core.hooksPath.
What ships with it
2 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 Changed · +100 lines d65fb8d18743
- 6d ago Changed · +32 lines 6efb0d7004e2
- 10d ago First seen · 130 lines · 73 tokens per session scan A fe09edae45d9
nemoclaw-contributor-create-pr is a skill published in the GitHub repository NVIDIA/NemoClaw (22,418 stars, last pushed yesterday), licensed Apache-2.0. It adds 73 tokens to every session and 3,663 once invoked, about $0.0004 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
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.
triage-contributor-pr
Triage open pull requests from external contributors to prisma/prisma and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming contributor PRs, to decide whether a fork PR is safe to run CI on, to check whether a PR is in scope for its version…
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
update-pr
Update the pull request for the current session. Use when the user wants to push new changes to an existing PR.
remember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…
code-review
Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.