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 SupercmoHQ/superCMO-skills --skill writing-video-scriptsgit clone --depth 1 https://github.com/SupercmoHQ/superCMO-skillsWrote 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/supercmohq/supercmo-skills/writing-video-scripts)<a href="https://agentmods.dev/skills/supercmohq/supercmo-skills/writing-video-scripts"><img src="https://agentmods.dev/badge/skills/supercmohq/supercmo-skills/writing-video-scripts/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/supercmohq/supercmo-skills/writing-video-scripts"><img src="https://agentmods.dev/badge/skills/supercmohq/supercmo-skills/writing-video-scripts.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 | $0.00108 | $0.01494 |
| Opus 5.5 | $0.00043 | $0.00598 |
| Sonnet 5.5 | $0.00022 | $0.00299 |
| Haiku 4.5 | $0.00011 | $0.00149 |
Grade A, and why
writing-video-scripts 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Script
Write the whole monologue first, to the video's total length, then cut it into one segment per clip.
Workflow
Step 1: Collect what the video has already fixed
These are decided before the script is written, and the writing has to fit inside them:
- a brief of what the words should communicate — the script is written from this, cut to fit the duration where it won't all fit
- how long the video runs in total
- how many clips it is, and how many seconds each one runs
- which beats of the story land in which clip — what happens on screen, not what gets said
- whether the words are spoken on camera or carried as a voiceover
- which claims may be made, if any
Where any of these is missing, ask for it rather than assuming it.
Step 2: Work out the budget
Speech runs at a fixed pace, so the word count isn't a style choice.
- Aim for 2-3 words per second of clip. That is the target — a 15-second clip wants about 30 to 40 words.
- Never go past three words per second. That is the ceiling, and it is the number Step 6 tests against. A 15-second clip fails at 46 words.
The gap between the two is deliberate: it is room for the pauses, the breath and the beats where the picture carries the moment. A segment written to the ceiling leaves none of that.
Add the per-clip budgets up against the total length before drafting anything. Where a segment runs long, cut words. Never speed up the delivery, and never stretch the clip to fit the writing.
Step 3: Write the hook
The first three seconds decide whether the rest gets watched, so write this line before any other.
- It fits in three seconds — six to ten words at speaking pace. The viewer has already decided by then, so a line that needs longer has arrived too late.
Pick one pattern and commit to it. These are the ones that recur across short-form:
- Problem — name a symptom the viewer is living with right now.
- Contrarian — contradict something the category takes as given.
- Curiosity — point at a specific thing they don't know and signal it's about to be answered.
- Result first — show the outcome with no explanation attached to it yet.
- Social proof — someone else's experience or number, often relayed rather than claimed. Only where real proof was supplied; otherwise this pattern is closed.
- Scenario drop-in — start mid-situation, already recognisable, with no setup.
- Pattern interrupt — an ordinary scene with one thing visibly wrong, played straight.
- Listicle — state a defined scope up front, so the viewer knows what they are committing to.
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 First seen · 112 lines · 108 tokens per session scan A 6b951e286baf
writing-video-scripts is a skill published in the GitHub repository SupercmoHQ/superCMO-skills (242 stars, last pushed 6d ago), licensed Apache-2.0. It adds 108 tokens to every session and 1,494 once invoked, about $0.0004 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
pkf-writing
Author, update, convert, validate, persist, and render PKF (.pkf) content through message-inline, Library Asset, or Memory Page carriers. Use for structured reports, knowledge pages, delivery cards, or any .pkf body. NOT for recall, memory-graph placement, or curation decisions — those belong to the memory skill.
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the chosen backdrop colour, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed…
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…
email-lifecycle-flow-writer
Step of the email-lifecycle playbook: writes one lifecycle flow as a build sheet for the brand's email tool, every message finished in the brand voice. Run email-lifecycle instead; not for direct use.
work-with-creators-creator-vetting
Vets creators you have already named from their public pages. Covers the median views of their last 12 to 20 posts (sponsored and organic apart), a read of their comments, how often they post, audience fit with how sure it is, about 12 months of brand-safety checks, rival partnerships and rules for regulated…
loop-engineering
Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns. Invoke when designing or debugging a skill that iterates (search-verify-retry, scan-until-dry, fetch-retry-gate).