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-pr-comparator/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-pr-comparator)<a href="https://agentmods.dev/skills/nvidia/nemoclaw/nemoclaw-maintainer-pr-comparator"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-maintainer-pr-comparator/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-pr-comparator"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-maintainer-pr-comparator.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 | $0.00030 | $0.01718 |
| Opus 5.5 | $0.00012 | $0.00687 |
| Sonnet 5.5 | $0.00006 | $0.00344 |
| Haiku 4.5 | $0.00003 | $0.00172 |
Grade A, and why
nemoclaw-maintainer-pr-comparator 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 1mo 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Comparator
Compare PRs for one issue. Tier 0 determines eligibility. Tiers 1 and 2 score correctness and quality. Tier 3 resolves ties. If no PR passes Tier 0, rank eligible PRs for salvage.
Prerequisites
ghCLI installed and authenticated- A target repository with an issue that has two or more open PRs
Repo policy
The defaults use NemoClaw conventions for CODEOWNERS, DCO, CodeRabbit, and docs/.
Read the canonical superseded-PR attribution policy in
../nemoclaw-maintainer-policies/references/workflow-policy.md.
Edit repo-policy.md for another repository.
Execute comparator helpers from a fetched canonical NVIDIA/NemoClaw main checkout, or verify
their executable code and dependencies against that revision before use. Candidate-modified helpers
must not receive GitHub credentials. Inspect helper source when needed; a section heading does not
establish trust.
Workflow
Step 1: Parse issue
Read the issue body and all comments. Extract each acceptance criterion:
gh issue view <issue-number> --json title,body,comments
Comments can add requirements that are absent from the issue body.
Step 2: Discover candidate PRs
scripts/find-candidates.sh <issue-number>
Applies a single default order with stop conditions.
Step 3: Detect supersession and transferred work
scripts/parse-supersession.sh <pr-number-1> <pr-number-2> ...
Parse the case-insensitive statement families implemented by scripts/parse-supersession.sh:
supersed[a-z]*before#N:supersedes #Npoints from the current PR to#N;superseded by #Npoints from#Nto the current PR.replac[a-z]*before#N:replaces #Npoints from the current PR to#N;replaced by #Npoints from#Nto the current PR.clos[a-z]* in favor ofbefore#N:closes in favor of #Nandclosed in favor of #Npoint from#Nto the current PR.fold[a-z]* inbefore#N:folds in #Npoints from the current PR to#N;folded into #Npoints from#Nto the current PR.
What ships with it
12 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.
- checks/tier-0-gates.md 3.6 KB
- checks/tier-1-correctness.md 3.7 KB
- checks/tier-2-quality.md 2.9 KB
- repo-policy.md 2.8 KB
- scripts/check-coderabbit-threads.sh 2.8 KB runs code
- scripts/collect-gates.sh 9.1 KB runs code
- scripts/find-candidates.sh 3.7 KB runs code
- scripts/parse-supersession.sh 2.5 KB runs code
- scripts/render-verdict.py 11 KB runs code
- templates/verdict.md 4.6 KB
- tiebreakers.md 3.7 KB
- validation/backtest.md 3.1 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.
- 1mo ago Changed · +4 lines 62c5979ff0a1
- 1mo ago Changed · -10 lines · -24 tokens per session 4ca4edeb7c62
- 2mo ago First seen · 167 lines · 54 tokens per session scan A a8f881177cfb
nemoclaw-maintainer-pr-comparator is a skill published in the GitHub repository NVIDIA/NemoClaw (22,871 stars, last pushed today), licensed Apache-2.0. It adds 30 tokens to every session and 1,718 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
update-skills
Create or update repository skills and instructions when major learnings are discovered during a session. Use when the user says "learn!", when a significant pattern or pitfall is identified, or when reusable domain knowledge should be captured for future sessions.
sync
Sync the current session branch with its upstream branch, or publish the current session branch to a remote. Use when the user asks to sync a branch, pull latest changes, rebase onto upstream, push current branch, publish branch, or set upstream.
merge
Merge changes from the topic branch to the merge base branch. Use when the user wants to merge their session's work back to the base branch.
publish-npm-version
Cuts the next release of Prisma 8: bumps the root package.json version (on the v8 RC line: 8.0.0-rc.N → rc.N+1), propagates it to every workspace package, and opens a PR titled "chore(release): bump to ". When the maintainer merges the PR, the Publish to npm workflow runs automatically and ships the new version to npm…
contrib-pr
Open a high-quality external contributor PR against prisma/orm. Use when the user is an outside contributor (not a Prisma maintainer) and wants to submit a change as a pull request from a fork. Encodes the contribution flow from CONTRIBUTING.md so the resulting PR passes review on the first round.
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.