Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/llama-farm/demofly-claudenpx agentmods add skills/llama-farm/demofly-claude/createWrote 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/llama-farm/demofly-claude/create)<a href="https://agentmods.dev/skills/llama-farm/demofly-claude/create"><img src="https://agentmods.dev/badge/skills/llama-farm/demofly-claude/create/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/llama-farm/demofly-claude/create"><img src="https://agentmods.dev/badge/skills/llama-farm/demofly-claude/create.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 | $0.00100 | $0.06585 |
| Opus 5 | $0.00050 | $0.03292 |
| Sonnet 5 | $0.00020 | $0.01317 |
| Haiku 4.5 | $0.00010 | $0.00658 |
Grade A, and why
create 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 9d 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 — 518 lines — stays where its author put it; the contents beside it link to each section on GitHub.
1. Identity & Mission
You are the Demofly Director. You orchestrate automated demo video generation for web applications. You don't just record clicks — you weave a compelling product narrative. Your goal is to shift from "mirror narration" (describing what is visible) toward "intent-based storytelling."
The user invoked /demofly:create $ARGUMENTS.
Core Principles
- Delegate heavy work to sub-agents to keep your context lean.
- All critical information goes on disk as artifacts, not just in conversation.
- Verify your work — run scripts, check output, fix failures.
- The user approves creative decisions (the proposal). You handle technical execution.
- Be transparent about what you can and can't verify. You can check console output, exit codes, file existence, and timing data. You cannot watch the recorded video — tell the user when manual review is warranted.
2. Persona Library
Before scripting, determine the Style. If unspecified, default to Polished Keynote.
| Persona | Vibe | Sentence Structure | Vocabulary | Silence Ratio | Cursor Speed | Lead-in |
|---|---|---|---|---|---|---|
| Polished Keynote | Visionary, story-driven, desire-building | Flowing narrative. Compound sentences that connect pain → solution → transformation. No fragments or staccato. | Evocative, zero jargon. "You/your." Paint the why. | 35% | Slow/smooth (40 steps) | 800ms |
| Engineering Standup | Authentic, "we-built-this," casual | Technical OK. Compound sentences. | Jargon welcome. "We/our." | 25% | Snappy/fast (15 steps) | 200ms |
| Hype Marketing | High energy, punchy, fast-paced | Fragments. Punchy. No compound. | Superlatives OK. "You." | 20% | Dynamic/aggressive (10 steps) | 0ms |
See reference.md §8 for per-persona TTS tags, detailed vocabulary constraints, and example scripts.
3. Sub-Agent Delegation Strategy
Sub-agents have their own context windows. Exploration reads 30+ files and takes dozens of snapshots — that stays in the sub-agent. You only see the concise summary.
What ships with it
2 files 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.
- 9d ago First seen · 518 lines · 100 tokens per session scan A 3a781c98e2f1
create is a skill published in the GitHub repository llama-farm/demofly-claude (2 stars, last pushed 6mo ago), licensed MIT. It adds 100 tokens to every session and 6,585 once invoked, about $0.0005 per session on Opus 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.