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 researchgit 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/research)<a href="https://agentmods.dev/skills/katipally/openlive/research"><img src="https://agentmods.dev/badge/skills/katipally/openlive/research/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/research"><img src="https://agentmods.dev/badge/skills/katipally/openlive/research.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 | $0.00028 | $0.00797 |
| Opus 5.5 | $0.00011 | $0.00319 |
| Sonnet 5.5 | $0.00006 | $0.00159 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
research 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Researching well
Good research answers the question asked, from sources that can be checked, and says plainly what is still uncertain.
Your tools
delegate(task): hands one task to OpenLive's research assistant, who hasweb_searchandfetch_urland reports back a short summary. It works while you keep talking and takes a few search steps at most, so give it one focused question per call.web_searchandfetch_url: if these are in your own tool list, call them directly instead of delegating. A coding agent may also have its own web tools; use whichever you have.
If you have none of these, say you cannot look it up right now and answer only from what you are sure of, marked as such.
1. Plan the questions
Before searching, break the request into the few facts that decide the answer. "Which laptop should I buy" becomes: the models in their budget, battery life measured by reviewers, current prices. Two to four focused questions beat one vague one.
Tell the user in one short line what you are checking, then start.
2. Ask for sources, every time
The assistant returns plain sentences and leaves links out unless asked. So write each delegated task to ask for them:
Find the current price of the Framework Laptop 13 in the US, from the official store, with the source URL.
Good task lines name: the exact fact, the time frame ("as of this month"), the kind of source you want (official site, the paper, the filing, a named outlet), and "with source URLs".
With web_search yourself: search, pick the most authoritative results, then
fetch_url them to read the page itself. Search highlights are a lead, not a
source.
3. Prefer primary sources
In order:
- The original: the official page, the paper, the dataset, the changelog, the court filing, the company's own announcement.
- A reputable outlet reporting on it, with a date.
- Everything else, only to find 1 or 2.
Check the date. For anything that changes (prices, versions, schedules, office holders, scores), an old page is a wrong answer.
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 · 86 lines · 28 tokens per session scan A 8a33d89dec5e
research is a skill published in the GitHub repository katipally/openlive (360 stars, last pushed 8d ago), licensed Apache-2.0. It adds 28 tokens to every session and 797 once invoked, about $0.0001 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.