Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/onedro1d/dark-factory/df-app-walkthrough)<a href="https://agentmods.dev/skills/onedro1d/dark-factory/df-app-walkthrough"><img src="https://agentmods.dev/badge/skills/onedro1d/dark-factory/df-app-walkthrough/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/onedro1d/dark-factory/df-app-walkthrough"><img src="https://agentmods.dev/badge/skills/onedro1d/dark-factory/df-app-walkthrough.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 | $0.00152 | $0.03103 |
| Opus 5 | $0.00076 | $0.01551 |
| Sonnet 5 | $0.00030 | $0.00621 |
| Haiku 4.5 | $0.00015 | $0.00310 |
Grade A, and why
df-app-walkthrough 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dark Factory — Autonomous App Walkthrough
Overview
Produces a finished walkthrough video of a running web application without a person speaking, clicking, or editing. Everything runs locally: a neural text-to-speech voice, a headless browser, and ffmpeg. No recording SaaS, no upload, no API key — which is what makes it usable on software you are not allowed to screen-share to a third party.
Four stages, each a script:
narration.json ──▶ build-narration ──▶ audio/*.wav + timing.json
│
▼
record-walkthrough ──▶ raw .webm + recorded-timeline.json
│
▼
assemble ──▶ walkthrough.mp4 ──▶ verify
This is a producer skill. Its natural upstream is a written demo script; its natural
downstream is df-video-intake (which turns a video back into text) — the two are inverses
and are useful in sequence when a recorded walkthrough must become requirements.
When to use
- "Record a walkthrough / demo / product tour of this app."
- A written demo script exists and someone has to perform it, repeatedly, on every release.
- A UI needs a narrated artefact for people who will never be given access to it.
- Regression-by-eye: re-record on each release and compare.
When not to use
- You need a person's own voice and improvisation — record that yourself.
- The thing being demonstrated is non-deterministic and slow (a long generation job). Narrate it over a card instead; see Cards below.
The load-bearing idea: audio first, video paced to audio
You cannot know how long a sentence takes until it has been spoken. So the narration is synthesized and measured before the browser opens, and the recorder holds each frame until that line has finished.
The recorder then emits the offset each step actually landed at, and assembly places audio and captions at those measured offsets rather than the planned ones. A step that runs long becomes a slightly longer pause instead of desynchronising everything after it.
What ships with it
10 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.
- package.json 562 B
- scripts/assemble.mjs 4.1 KB runs code
- scripts/build-narration.mjs 3.0 KB runs code
- scripts/check-prereqs.sh 2.5 KB runs code
- scripts/lib/actions.mjs 7.3 KB runs code
- scripts/lib/session.mjs 5.8 KB runs code
- scripts/record-walkthrough.mjs 4.2 KB runs code
- scripts/setup.sh 2.3 KB runs code
- scripts/verify.mjs 3.4 KB runs code
- templates/narration.example.json 3.6 KB
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 · 294 lines · 152 tokens per session scan A fd55ce0d66c9
df-app-walkthrough is a skill published in the GitHub repository OneDro1d/dark-factory (0 stars, last pushed today), licensed Apache-2.0. It adds 152 tokens to every session and 3,103 once invoked, about $0.0008 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 2026-09-01.
Other skills, from other repositories
feature-demo-recording
Record a demo video of a web feature from a real browser. Two modes -- a NARRATED film where measured voiceover drives the timeline (designed slides, subtitles, punch-in camera, rendered from an HTML timeline), and a SILENT evidence clip for a PR or a QA pass. Use when the user asks to record a video, demo, or screen…
browser-video-recording
Create polished 60 fps 4:3 4K browser screen-recording style videos from Codex in-app browser captures, with browser-only crop, natural macOS cursor styling, deliberate click choreography, zoom-follow framing, ffprobe/thumbnail verification, and optional native recording compatibility checks. Use when the user asks to…
html-to-video-pipeline
Reliable HTML-to-MP4 rendering via headless browser recording (Playwright/Puppeteer) + ffmpeg — the ordering, gotchas, and verification steps you MUST get right or the output silently rots. Trigger whenever the user is building or debugging any pipeline that turns an HTML/CSS/JS page (single-file, multi-composition…
record-video
Record and upload a short browser interaction video artifact.
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.