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 katipally/openlive --skill connector-setupgit clone --depth 1 https://github.com/katipally/openliveWrote 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/katipally/openlive/connector-setup)<a href="https://agentmods.dev/skills/katipally/openlive/connector-setup"><img src="https://agentmods.dev/badge/skills/katipally/openlive/connector-setup/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/katipally/openlive/connector-setup"><img src="https://agentmods.dev/badge/skills/katipally/openlive/connector-setup.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00042 | $0.00882 |
| Opus 5.5 | $0.00017 | $0.00353 |
| Sonnet 5.5 | $0.00008 | $0.00176 |
| Haiku 4.5 | $0.00004 | $0.00088 |
Grade A, and why
connector-setup 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 12d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setting up connectors
A connector is an MCP server that gives every brain in OpenLive more tools.
Its tools show up as <connector>__<tool> once it is connected. You help the
user add one, sign in, and fix one that is not working.
Your tools: list_connectors, add_connector, connector_sign_in,
reconnect_connector.
Secrets
- Never ask the user to say an API key or token out loud, and never repeat one back. Suggest they paste it in Settings, Capabilities, Connectors, where it is stored encrypted.
- If they paste one to you, pass it in
headers(or insidejson) and do not mention its value again. Tool results never show it.
Adding one
- Find out which server. Most services document either:
- A URL (a remote server), as
https://mcp.example.com/mcp. Calladd_connectorwithurland a shortname. - A JSON block in the
mcpServersshape, with acommandsuch asnpx(a local server). Calladd_connectorwithjsonset to that block, as text.
- A URL (a remote server), as
- The user is asked to approve the add. Then read the result:
- connected: done. Say how many tools it offers.
- needs sign-in: go to "Signing in".
- waiting for the user to allow it to run: a local server runs a
program on their computer, so only the user can allow it: Settings,
Capabilities, Connectors, then Review and Allow on that connector. You
cannot allow it, and no tool can.
Tell them where to click, then check with
list_connectors. - failed: go to "Fixing one".
If they do not know the URL or JSON, offer to look it up (the research skill) on the service's own documentation site.
Signing in
For a connector that needs sign-in, call connector_sign_in with its id. It
opens the service's sign-in page in their browser, or gives you the address
to pass on. Ask them to finish signing in there, then call list_connectors
to confirm it is connected.
Only remote (URL) connectors sign in. A local one takes its keys as env values in Settings, Capabilities, Connectors.
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.
- 12d ago First seen · 78 lines · 42 tokens per session scan A 51c305dae302
connector-setup is a skill published in the GitHub repository katipally/openlive (360 stars, last pushed 8d ago), licensed Apache-2.0. It adds 42 tokens to every session and 882 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 2026-10-04.
Other skills, from other repositories
frontend-design
Aesthetic direction for OrkasVideoStudio HTML and motion-graphics compositions. Use before stage-compose writes composition-manifest.json artdirection and index.html to choose a subject-specific visual point of view, type, palette, layout signature, restrained motion, and anti-template checks.
gate-control
Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition.…
stage-edit
Intelligent editing of real user-supplied footage—understand it with transcript/inspected-frame/scene/silence/quality evidence, then choose deterministic timeline operations or a constrained semantic AI edit. Trigger for repurpose, montage, cleanup, localization, narration, or local content changes.
design-system-importer
Reference-media and design-system input layer for OrkasVideoStudio. Treat reference images, videos, screenshots, brand guides, and design notes uniformly, compiling reproduce/edit/guide intent into executable spatial and temporal constraints.
brain-setup
Bootstrap the Open Project Brain Standard into the current project — prefer brain init (ensure BRAIN.md, scaffold empty brain brainRoot-aware, default-wire CLAUDE.md + AGENTS.md). Optionally install a pre-commit hook and a Claude Code or Codex SessionStart hook.
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.