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 skill-creatorgit 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/skill-creator)<a href="https://agentmods.dev/skills/katipally/openlive/skill-creator"><img src="https://agentmods.dev/badge/skills/katipally/openlive/skill-creator/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/skill-creator"><img src="https://agentmods.dev/badge/skills/katipally/openlive/skill-creator.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 | $0.00648 |
| Opus 5.5 | $0.00011 | $0.00259 |
| Sonnet 5.5 | $0.00006 | $0.00130 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
skill-creator 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Making a skill from what the user describes
A skill is a short set of instructions any brain in OpenLive loads when a task
matches its description. You turn the user's workflow into one, show it, and
save it with save_skill once they agree.
1. Ask what it is for
Ask only what you need, one or two questions at a time:
- What task is this for, and when should it kick in?
- What are the steps, in order? What does "done" look like?
- Any rules: tone, format, tools to use or avoid, things never to do?
- An example of a good result, if they have one.
If they already described it fully, skip straight to the draft.
2. Draft it
Name. Lowercase letters, digits and single hyphens, at most 64
characters, no hyphen at the start or end. Short and plain: weekly-report,
pr-review, meeting-notes.
Do not reuse the name of a built-in skill (computer-use, research,
skill-creator, connector-setup). Only if the user says they want their own
version to replace a built-in one, save it under that name with
replace_built_in: true.
Description. One line, at most 1024 characters, starting with "Use when" and naming the situations that should trigger it. This line is all a model sees before loading the skill, so make it specific:
- Weak: "Helps with reports."
- Strong: "Use when the user asks for their weekly status report or a summary of what they shipped this week."
Body. Markdown instructions, written to the model that will follow them:
- Start with one line on the goal.
- Numbered steps for the workflow, each one action.
- The user's rules as short bullets.
- A small example of the output if format matters.
- Keep it under about 500 lines. Leave out anything a capable model already knows; keep what is specific to this user.
3. Show it
Read or show the draft to the user: the name, the description and the body. In a spoken call, summarize the body in a few sentences and offer to read it in full. Ask: "Shall I save it?" Change it until they are happy.
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 · 69 lines · 28 tokens per session scan A 06d7568a4e16
skill-creator 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 648 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.