NemoClaw: Skill for Claude Code

.agents/skills/nemoclaw-maintainer-find-review-pr/SKILL.md

nemoclaw-maintainer-find-review-pr is a skill for Claude Code from NVIDIA/NemoClaw. It costs 76 tokens per session (1,638 once invoked), scanned A, original, Apache-2.0.

A tool that finds open GitHub pull requests marked for security work and given Urgent or High priority in the project tracker. It links each pull request to its issue and checks for competing or replaced proposals.

In plain words
What is it for?
Use it to select the next security pull request to review and identify duplicate, competing, or superseded pull requests.
Why use it?
It helps maintainers find the most urgent security reviews without searching the project manually.

Skill for Claude Code ✓ vendor

Written for Claude Code: user-invocable in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is NVIDIA/NemoClaw's own configuration. It tells Claude Code how to work on NemoClaw itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything NemoClaw configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is ../nemoclaw-maintainer-pr-comparator/scripts/parse-supersession.sh <pr-number-1> <pr-number-2> ....

About the project

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.

NVIDIA/NemoClaw · 22,442 stars · on GitHub · docs.nvidia.com

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/NVIDIA/NemoClaw/main/.agents/skills/nemoclaw-maintainer-find-review-pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/NVIDIA/NemoClaw

Made for: Claude Code.

Wrote 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.

agentmods badge for nemoclaw-maintainer-find-review-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-maintainer-find-review-pr/github.svg)](https://agentmods.dev/skills/nvidia/nemoclaw/nemoclaw-maintainer-find-review-pr)
Your own site
<a href="https://agentmods.dev/skills/nvidia/nemoclaw/nemoclaw-maintainer-find-review-pr"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-maintainer-find-review-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.

agentmods 80×15 button for nemoclaw-maintainer-find-review-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/nvidia/nemoclaw/nemoclaw-maintainer-find-review-pr"><img src="https://agentmods.dev/badge/skills/nvidia/nemoclaw/nemoclaw-maintainer-find-review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,638 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Snyk warn 7 Sept 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.01638
Opus 5 $0.00038 $0.00819
Sonnet 5 $0.00015 $0.00328
Haiku 4.5 $0.00008 $0.00164

Measured 13d ago against content hash 82b889a184fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

nemoclaw-maintainer-find-review-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 13d 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.

.agents/skills/nemoclaw-maintainer-find-review-pr/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Find PR to Review

Find open PRs with the security label and Project Priority Urgent or High. Link each PR to its issue. Identify competing or superseded PRs. Report the results for the maintainer.

Prerequisites

  • gh (GitHub CLI) must be installed and authenticated.
  • The active gh token must have read:project scope.
  • You must be in a GitHub repository (or the user must specify OWNER/REPO).

Step 1: Fetch candidate PRs

Read the NemoClaw Development Tracker and select open PRs that carry the canonical security label and have Project Priority Urgent or High:

gh project item-list 199 --owner NVIDIA --limit 1000 --format json \
  | jq '[.items[]
    | select(.content.repository == "NVIDIA/NemoClaw")
    | select(.content.type == "PullRequest")
    | select(((.labels // []) | index("security")) != null)
    | select(.priority == "Urgent" or .priority == "High")
    | {number: .content.number, title: .content.title, url: .content.url,
       priority: .priority, status: .status}]'

Remove entries for closed PRs. For each remaining PR, fetch the body, author, branch, labels, and creation time with gh pr view. If no PRs remain, report that result and stop.

Step 2: Extract linked issues

For each PR, search its body for issue references. Match these patterns without case sensitivity:

  • Fixes #NNN, Closes #NNN, Resolves #NNN, Refs #NNN, Relates to #NNN, or Part of #NNN
  • Related issues / Linked issues section containing #NNN
  • Issue number in the PR title, such as a (#NNN) suffix
  • Branch name containing an issue number, such as fix/something-NNN

Build a mapping: PR# → [issue numbers].

If a PR has no detectable linked issue, mark it as (no linked issue).

Step 3: Detect duplicates

Group PRs by linked issue number. If two or more open PRs link to one issue, put them in one competing-PR group.

Read the full file on GitHub · 154 lines

Changes

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.

  1. 13d ago First seen · 154 lines · 76 tokens per session scan A 82b889a184fb

Subscribe to this mod's changes

nemoclaw-maintainer-find-review-pr is a skill published in the GitHub repository NVIDIA/NemoClaw (22,442 stars, last pushed today), licensed Apache-2.0. It adds 76 tokens to every session and 1,638 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.

Related

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.

jd-opensource/JoySafeter · 36 tokens

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…

prisma/orm · 131 tokens

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.

prisma/orm · 38 tokens

no-bare-casts

Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.

prisma/orm · 52 tokens

update-pr

Update the pull request for the current session. Use when the user wants to push new changes to an existing PR.

microsoft/vscode · 26 tokens

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…

langchain-ai/deepagents · 71 tokens