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/maneja81/openorbit/run-openorbitnpx skills add maneja81/OpenOrbit --skill run-openorbitgit clone --depth 1 https://github.com/maneja81/OpenOrbitWrote 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/maneja81/openorbit/run-openorbit)<a href="https://agentmods.dev/skills/maneja81/openorbit/run-openorbit"><img src="https://agentmods.dev/badge/skills/maneja81/openorbit/run-openorbit.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00048 | $0.03698 |
| Opus 5 | $0.00024 | $0.01849 |
| Sonnet 5 | $0.00010 | $0.00740 |
| Haiku 4.5 | $0.00005 | $0.00370 |
Grade C, and why
run-openorbit scanned grade C with 1 finding 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf node_modules/electron/dist node_modules/electron/path.txt && node node_modules/electron/install.js How it starts
The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenOrbit is an Electron desktop app. Drive it through the Playwright REPL at
.claude/skills/run-openorbit/driver.mjs. Launch takes ~5s, so the REPL beats relaunching per
interaction.
Paths below are relative to the repo root. On macOS no xvfb is needed; on headless Linux prefix
with xvfb-run -a.
Read this first — the sandbox is not optional
app.getPath("userData") resolves to ~/Library/Application Support/OpenOrbit from every
checkout and every git worktree. There is no per-branch data directory. Launching the app to
try something out therefore writes into the developer's real database: settings, chat history,
agents, and encrypted API keys.
The driver always passes --user-data-dir and aborts the launch if app.getPath("userData")
doesn't land inside the sandbox. Don't remove that check, and don't launch the app by hand from a
worktree to "just have a look".
Sandbox defaults to /tmp/orbit-run/userdata — override with ORBIT_USER_DATA. Because it
starts empty, the first launch is a genuine fresh install: onboarding, empty database. That is
usually what you want for testing defaults; reset gets you back to it.
Build
npm install # once per worktree — node_modules is not shared
npm run build # main is dist-electron/main/index.js; the driver checks it exists
⚠ Check the Electron binary after installing — the install lies. npm ci / npm install in a
fresh worktree regularly exits 0 having left no usable Electron. Two variants seen: the binary
missing entirely (dist and path.txt both absent), and a half-extracted app (failed to create directory …/Electron.app/Contents/Resources/kn.lproj: File exists). The driver then can't launch,
and vitest quietly loses electron/main/ai/agents.test.ts — 45 tests.
ls node_modules/electron/path.txt node_modules/electron/dist # both must exist
# repair:
rm -rf node_modules/electron/dist node_modules/electron/path.txt && node node_modules/electron/install.js
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.
- 4d ago First seen · 281 lines · 48 tokens per session scan C 7b9b9467b088
run-openorbit is a skill published in the GitHub repository maneja81/OpenOrbit (10 stars, last pushed 12d ago), licensed MIT. It adds 48 tokens to every session and 3,698 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
dogfood-as-user
How to dogfood and verify a Gini behavior change by driving a real chat turn as a real user would. Use when verifying that the agent reaches for a tool or path on its own — a behavioral steer, a new tool, an INSTRUCTIONS.md change, or a dispatch/provider/memory/skill change — or before claiming a steer "works".…
Abu-Browser
操作阿布应用内置的可见浏览器：打开网页、点击、填写、截图和提取数据。用户要求在阿布内预览或操作网页时使用；无需安装浏览器扩展。.
browser-qa
QA de navegador y regresión visual con Playwright: navegación, capturas (viewport/página/elemento), comparación contra baseline, snapshots de accesibilidad e inspección de red/consola/DOM, cross-browser.
mnemosyne-memory
Give your agent a sovereign, governed long-term memory backed by Mnemosyne OS. Use whenever the user has Mnemosyne OS installed and you need to recall past decisions, project history, or notes across sessions — or to persist something worth remembering. Teaches the vault governance rules every agent must honor before…
connect-agent
Connect the codebase's AI agent to LangWatch agent simulations, so test suites run against the real agent process. Adds a small connect function beside the service startup that calls the agent already in the codebase, which opens an outbound connection and registers the agent with its environment and its run…
writing-e2e-flows
Use when a feature or fix in future-agi needs an end-to-end Playwright flow under e2e/ — a new flow for user-visible behaviour, an update to a flow whose pinned endpoint, route, table or selector changed, or when a review flagged missing E2E coverage. Also use to check whether an existing flow already pins an…