video-cost-estimate
Skill1 starsChanged 4 months agoMITView on GitHub
Produce an itemized cost sheet for ONE YouTube video — voice, avatar, render, tooling — in USD. Self-improving: reads past estimates vs actuals, logs after. Use when the user asks "how much per video", "cost of this video", "video budget", or plans an episode. Agentic OS (Level 1).
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 34
Never quote a rate without labeling it an assumption if unverified.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
video-cost-estimate
Itemized $ cost for a single episode. Grounds on your real video pipeline.
Loop (every time)
- Before — read
<vault>/agentic-os/runs/video-cost-estimate.md. Applylesson:(esp. actual-vs-estimate deltas). Standing facts (verify before quoting — see user memory):- ElevenLabs: key is pay-as-you-go; (if a cloned voice is unavailable on your plan, use a stock pro voice). Price per 1k chars, count script chars.
- HeyGen avatar: credits/minute of avatar video — count final runtime minutes.
- Remotion render: local = compute/time only (≈ $0 cash) unless cloud render used.
- Claude/API: script + package generation tokens (usually plan-covered).
Steps
- Get inputs: script length (chars), final runtime (min), languages/variants (longform + vertical Short).
- Line items: voiceover (chars × EL rate), avatar (min × HeyGen rate), render (local≈0 or cloud), thumbnail, misc.
- Multiply by variant count (landscape + vertical + per-language).
- Show per-video total + per-variant breakdown + assumptions/rates used.
After
Append run: inputs, estimated total, (later) actual, lesson: on any rate drift.
Output to user
Markdown cost table, USD, one total line. State every rate assumption so it's auditable.
Never
- Never quote a rate without labeling it an assumption if unverified. Never omit the variant multiplier.
In this repository6 other files it gives its agents.
- deploy-verifySkill
- episode-packageSkill
- localize-humanizeSkill
- seo-guardSkill
- skill-onboardSkill
- verify-swarmSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.