OpenShell is a runtime for autonomous AI agents that executes them in sandboxed environments governed by declarative policies. It is used to restrict agents' access to files, credentials, data, and network resources, and the catalogue includes skills and workflows for operating and contributing to it.
Borrowing it
Nothing to install: this file belongs to NVIDIA/OpenShell. 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/OpenShell/main/.agents/skills/review-github-pr/SKILL.mdgit clone --depth 1 https://github.com/NVIDIA/OpenShellWrote 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/openshell/review-github-pr)<a href="https://agentmods.dev/skills/nvidia/openshell/review-github-pr"><img src="https://agentmods.dev/badge/skills/nvidia/openshell/review-github-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/openshell/review-github-pr"><img src="https://agentmods.dev/badge/skills/nvidia/openshell/review-github-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 | $0.00072 | $0.01944 |
| Opus 5.5 | $0.00029 | $0.00778 |
| Sonnet 5.5 | $0.00014 | $0.00389 |
| Haiku 4.5 | $0.00007 | $0.00194 |
Grade A, and why
review-github-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 6d 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review GitHub Pull Request
Summarize a GitHub pull request diff, highlighting key design decisions and notable code snippets.
Prerequisites
- The
ghCLI must be authenticated (gh auth status) - You must be in a git repository with a GitHub remote
Step 1: Resolve the PR
The user will provide either a PR number (e.g., #123 or 123) or a branch name. Determine which input was given and resolve it to a PR.
If a PR number is provided
Strip any leading # and use the numeric ID directly. Proceed to Step 2.
If a branch name is provided
Look up the open PR whose head branch matches:
gh pr list --head "<branch>" --state open
- If exactly one PR is found, extract its number and proceed to Step 2.
- If multiple PRs are found, list them and ask the user which one to review.
- If no PR is found, skip Step 2 (no PR description to fetch) and go directly to Step 3 using the local git diff fallback.
Step 2: Fetch PR Description
Retrieve the PR metadata:
gh pr view <number> --json title,body,state,headRefName,baseRefName,labels,author,closingIssuesReferences
Record the title, body, headRefName, and baseRefName for use in later steps.
Check Issue Acceptance
Inspect every closing issue reference (paginate as needed) and fetch its current repository and labels. Verify the PR author's permission in the target repository:
gh api repos/OWNER/REPO/collaborators/AUTHOR/permission --jq .permission
Call out each linked issue missing state:accepted, with an issue link. Verified
write, maintain, or admin access permits the exception; report it as context,
not a blocking concern. Other authors need at least one target-repository issue,
and every linked issue must be accepted; report violations under Potential
Concerns. PR body text such as No issue required does not bypass this gate.
Report failed lookups as unverified and continue the code review. For a branch
without a PR, note that issue acceptance was not verified.
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.
- 6d ago Changed f7c3e0ed646f
- 18d ago Changed · +1 lines 58ca7ccd9569
- 24d ago Changed · +17 lines 947fcff78e53
- 1mo ago Changed d1f649d536fc
- 2mo ago Changed · +2 lines 48600a21eb2d
- 2mo ago First seen · 180 lines · 72 tokens per session scan A c5ec1e430b55
review-github-pr is a skill published in the GitHub repository NVIDIA/OpenShell (21,172 stars, last pushed yesterday), licensed Apache-2.0. It adds 72 tokens to every session and 1,944 once invoked, about $0.0003 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.
review-github-pr compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| review-github-prNVIDIA/OpenShell | Skill | 21k | yesterday | Apache-2.0 | A | 72 | Claude Code, Codex |
| prYeachan-Heo/oh-my-claudecode | Skill | 41k | yesterday | MIT | A | 47 | Claude Code |
| merge-batchdiegosouzapw/OmniRoute | Skill | 83k | 5d ago | MIT | A | 46 | Claude Code |
| otto-pr-review-loopomnigent-ai/omnigent | Skill | 11k | today | Apache-2.0 | A | 17 | Claude Code, Codex |
| engram-branch-prGentleman-Programming/engram | Skill | 7.8k | today | MIT | A | 37 | Claude Code, Codex |
| github-contributordaymade/claude-code-skills | Skill | 1.5k | yesterday | MIT | A | 105 | Claude Code, Codex |
| revdiffumputun/revdiff | Skill | 945 | yesterday | MIT | A | 250 | Claude Code |