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 Orkas-AI/Orkas-VideoStudio --skill stage-editgit clone --depth 1 https://github.com/Orkas-AI/Orkas-VideoStudioWrote 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/orkas-ai/orkas-videostudio/stage-edit)<a href="https://agentmods.dev/skills/orkas-ai/orkas-videostudio/stage-edit"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-videostudio/stage-edit/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/orkas-ai/orkas-videostudio/stage-edit"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas-videostudio/stage-edit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00062 | $0.02239 |
| Opus 5.5 | $0.00025 | $0.00896 |
| Sonnet 5.5 | $0.00012 | $0.00448 |
| Haiku 4.5 | $0.00006 | $0.00224 |
Grade A, and why
stage-edit 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 1mo 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
stage-edit
How to intelligently edit real user-supplied footage while keeping source and decisions auditable. Deterministic operations handle cuts, joins, captions, overlays, reframes, and audio. When the request changes pixels semantically—remove an object, alter a background, relight, or make another content-aware local change—keep the EDIT route and execute only that bounded segment as a signed ovs video --operation edit call after paid-generation approval.
Subtitle safety hard rule. Burn captions only through ovs edit burnsubs; do not hand-write ffmpeg subtitle, drawtext, or PNG-overlay fallback commands. If burnsubs fails because the runtime ffmpeg lacks subtitle filter support, stop and report the blocker instead of improvising a custom ffmpeg graph.
If the task is to FIND / SELECT / REDUCE / CLEAN rather than run a known timecode edit — remove dead air, drop fillers, pick highlights, cut a long recording down — read stage-decide first: it covers understanding the footage and producing an evidence-bearing rough cut (the deterministic auto-cuts ovs edit trim-silence / remove-fillers, plus ovs scenes / ovs quality / ovs plan rank-takes). This skill is for executing cuts you have already chosen.
Two assembly paths — pick by whether the result needs to stay re-editable:
- Plan-backed (anything the user may later adjust: narration, multi-shot, segmented edits). Author
project/plan.json(the segments EDL — seestage-plan) carrying ONLY the operations the user asked for (the deltas) — everything else is the source, passed through untouched. Keep each editable concern SEPARATE in the plan: each narration line intracks.narration.segmentswith its ownproduced_path, each caption intracks.captions.linesas data, each segment carryingstatus/produced_path. Assemble withovs edit(trim → concat → mix → burnsubs). Because plan.json holds every piece separately, a later "fix one caption / re-voice one line" is a one-entry edit + one re-render — do NOT pre-bake (e.g. one big narration file), which destroys that separability. - One-shot deterministic (a plain trim or concat the user just wants done). Use
ovs editdirectly; write no plan.json.
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.
- 1mo ago Changed f181fc12dd1c
- 1mo ago Changed · -24 lines 2889a31cf268
- 1mo ago First seen · 108 lines · 62 tokens per session scan A ce0adfade119
stage-edit is a skill published in the GitHub repository Orkas-AI/Orkas-VideoStudio (329 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 2,239 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 2026-08-30.
Other skills, from other repositories
claude-real-video
Watch a video for the user. Use when the user shares a video URL (YouTube etc.) or local video file and wants it summarized, analyzed, or discussed — Claude can't ingest video directly, so this skill extracts scene-aware keyframes + transcript first, then reads those.
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.
issue-resolve
Use when an assessed gflow-cli issue (verdict CONFIRMED-BUG or LIKELY-BUG) has localized, verifiable scope and should be driven to a fix. Mutating and gated: it works in an isolated worktree, fixes test-first, and opens a DRAFT PR for human review. Built to run autonomously (hermes-ops) within a strict action envelope…
issue-assessment
Use when triaging a GitHub issue for gflow-cli — a reporter's bug claim, a freshly-filed issue, or deciding whether and how to act on one. Also use when an autonomous agent (hermes-ops) picks up a labelled issue. Read-only: produces a verdict, an end-to-end-verifiability judgment, and a reporter-facing reply. Does not…
live-verify
Two-part gate for gflow-cli feature/fix work. Part 1 (Pre-flight): use when starting work on a gflow-cli feature or fix — confirms the checkout reflects current develop before investing effort. Part 2 (Live-verify): use before claiming gflow-cli work done, especially anything touching a generation code path…
sonar
Check the SonarCloud quality gate for a PR (or the current branch) and drive it to zero. Reports GREEN, or the exact PR-scoped new issues/hotspots/coverage gaps to fix.