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 agentmods add skills/openhands/extensions/setup-openhandsnpx skills add OpenHands/extensions --skill setup-openhandsgit clone --depth 1 https://github.com/OpenHands/extensionsWhat 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 | $0.00055 | $0.00525 |
| Opus 5 | $0.00028 | $0.00262 |
| Sonnet 5 | $0.00011 | $0.00105 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
setup-openhands 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 2d 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.
What it actually says
Set Up OpenHands for a Repository
Work through these steps in order.
Step 1: Create AGENTS.md
Run setup-agents-md to generate a root-level AGENTS.md from the repo's actual
CI workflows, build files, and documentation.
Step 2: Create .openhands/setup.sh
Create .openhands/setup.sh — a bootstrap script that runs at the start of
every OpenHands session. Read the repo's CI workflows, AGENTS.md, and build
files to determine the correct commands. The script should:
- Install dependencies (the project's actual install command)
- Set required environment variables
- Run any other bootstrap steps (e.g. copy
.env.exampleto.env)
Keep it idempotent and fast. Use the real commands from CI, not generic examples.
Docs: https://docs.openhands.dev/openhands/usage/customization/repository#setup-script
Step 3: Create .openhands/pre-commit.sh
Create .openhands/pre-commit.sh — runs before every commit OpenHands makes.
Read the repo's CI workflows to find the lint and test commands, then mirror
them in the script. Exit non-zero on failure so the agent gets immediate
feedback instead of waiting for CI.
The script should run the same checks CI runs — if CI runs ruff check and
pytest, run those. If it runs cargo clippy and cargo test, run those.
Docs: https://docs.openhands.dev/openhands/usage/customization/repository#pre-commit-script
Step 4: Set up PR review
Run setup-pr-review to create the GitHub Actions workflow and walk the user
through configuration.
Step 5: Verify
Confirm all files exist and are correct:
AGENTS.mdat repo root with real commands (not boilerplate).openhands/setup.shwith the project's actual install/bootstrap commands.openhands/pre-commit.shmirroring the CI lint/test checks.github/workflows/pr-review.ymlwith valid YAML
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.
- 2d ago First seen · 57 lines · 55 tokens per session scan A 1c2381e0c154
setup-openhands is a skill published in the GitHub repository OpenHands/extensions (137 stars, last pushed 4d ago), licensed MIT. It adds 55 tokens to every session and 525 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…