Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add OpenHands/extensions --skill setup-pr-reviewgit clone --depth 1 https://github.com/OpenHands/extensionsWrote 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/openhands/extensions/setup-pr-review)<a href="https://agentmods.dev/skills/openhands/extensions/setup-pr-review"><img src="https://agentmods.dev/badge/skills/openhands/extensions/setup-pr-review/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/openhands/extensions/setup-pr-review"><img src="https://agentmods.dev/badge/skills/openhands/extensions/setup-pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00044 | $0.00730 |
| Opus 5.5 | $0.00018 | $0.00292 |
| Sonnet 5.5 | $0.00009 | $0.00146 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade A, and why
setup-pr-review 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set Up OpenHands PR Review
Add the PR review workflow to a GitHub repository so an OpenHands agent can review pull requests and post inline comments.
Docs: https://docs.all-hands.dev/sdk/guides/github-workflows/pr-review
Step 1: Create the workflow file
Create .github/workflows/pr-review.yml in the target repo. Fetch the latest
example from https://docs.all-hands.dev/sdk/guides/github-workflows/pr-review
and use it as the starting template. The workflow calls the
OpenHands/extensions/plugins/pr-review composite action directly.
Step 2: Configure the LLM
Ask the user whether they are using the OpenHands app (app.all-hands.dev) or their own LLM provider (e.g. Anthropic, OpenAI directly).
OpenHands app (default)
OpenHands app users already have access to an LLM API key through the OpenHands litellm proxy. Tell them:
Go to https://app.all-hands.dev → Account → API Keys → OpenHands LLM Key, and copy your key. Then add it as a GitHub repository secret: Settings → Secrets and variables → Actions → New repository secret. Name it
LLM_API_KEY.
Set these inputs in the workflow with: block:
llm-model: litellm_proxy/claude-sonnet-4-5-20250929llm-base-url: https://llm-proxy.app.all-hands.dev
Own LLM provider
If the user has their own API key (e.g. from Anthropic or OpenAI), tell them
to add it as a repository secret named LLM_API_KEY using the same path
above. Leave llm-base-url unset and set llm-model to the provider-prefixed
model name (e.g. anthropic/claude-sonnet-4-5-20250929).
You cannot create secrets — the user must do it manually. Do not ask for the key value. Just tell them where to put it.
Step 3: Ask the user for preferences
Present these options and apply any requested changes to the workflow file:
Review style (default: roasted)
roasted— Linus Torvalds-style, blunt, focuses on data structures and simplicity.standard— balanced, covers style/readability/security.
When to trigger (default: on-demand only)
- On-demand: add
review-thislabel or requestopenhands-agentas reviewer. - Automatic: review every new PR. Add
openedandready_for_reviewtoon.pull_request.typesand matching conditions to theif:block.
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.
- 1mo ago First seen · 73 lines · 44 tokens per session scan A 70b8d5fb4461
setup-pr-review is a skill published in the GitHub repository OpenHands/extensions (167 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 730 once invoked, about $0.0002 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…