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/mrieck/demoday-claude-pluginnpx agentmods add skills/mrieck/demoday-claude-plugin/demo-captureWrote 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/mrieck/demoday-claude-plugin/demo-capture)<a href="https://agentmods.dev/skills/mrieck/demoday-claude-plugin/demo-capture"><img src="https://agentmods.dev/badge/skills/mrieck/demoday-claude-plugin/demo-capture/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/mrieck/demoday-claude-plugin/demo-capture"><img src="https://agentmods.dev/badge/skills/mrieck/demoday-claude-plugin/demo-capture.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 | $0.00071 | $0.02132 |
| Opus 5 | $0.00036 | $0.01066 |
| Sonnet 5 | $0.00014 | $0.00426 |
| Haiku 4.5 | $0.00007 | $0.00213 |
Grade A, and why
demo-capture 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 10d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capturing the screen
Rehearse, then perform
The rehearsal session (demo_* MCP tools) is for figuring things out. The
performance runner replays what you found, smoothly, while recording.
Consequences worth internalising:
- Anything you do during rehearsal is invisible in the final video. Explore freely.
- Only successful actions are recorded, so a failed click cannot poison a script.
- The performance replays exactly the recorded steps. If the app needs to be in a particular state to start, put that in the action script or reset the app before performing.
Writing a flow that films well
- One idea per scene. If narration needs "and then", it is two scenes.
- Start where the user starts. Not on a page you navigated to off-camera.
- Type realistic content. "Acme Demo" reads as a demo. "asdf" reads as a bug.
- Pause after the payoff. Add
dwellMson the step that produces the result; the viewer needs a beat to see what changed. - Highlight the moment that matters. One
demo_highlightper scene, on the thing the narration is naming. More than one and none of them land. - Never demo a login. Use
storageStateor log in beforemarkStart.
Pacing to the narration
--target-duration stretches dwell, never motion. The clip lands on the
voiceover instead of being cut to fit afterwards.
pinToWord goes further: a step fires exactly when a word is spoken.
{ "type": "click", "selectors": ["[data-testid=save]"],
"label": "Save", "pinToWord": "save" }
Use word#2 for the second occurrence. Requires the scene's .words.json, passed
as --timestamps.
If the runner warns about overrun, the steps genuinely cannot fit — cut steps or lengthen the line. It will not silently speed up the cursor.
Web specifics
- The cursor in the video is drawn, because Playwright's real pointer is invisible to the recorder. It is animated with the Web Animations API rather than requestAnimationFrame, which does not fire reliably under headless capture.
- Prefer
demo_inspectselectors. The ladder (data-testid→ id → role+name → text → structural path) is tried in order, so replay survives small DOM changes. - Headless is fine and slightly more reliable; use headed when you want to watch.
- Authenticated sessions:
--storage-state <file>.
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.
- 10d ago First seen · 197 lines · 71 tokens per session scan A 4f782d04cac7
demo-capture is a skill published in the GitHub repository mrieck/demoday-claude-plugin (2 stars, last pushed 7d ago), licensed MIT. It adds 71 tokens to every session and 2,132 once invoked, about $0.0004 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
youtube-producer
Plans, packages, and scripts long-form video for retention and channel growth — idea selection, titles and thumbnails, script structure, and diagnosing why a video or channel underperforms. Use this for video ideas, packaging, scripting, a retention teardown, or channel strategy — including when someone describes a…
video-content
Plans and scripts short-form and long-form video, and designs the packaging — titles, thumbnails, and openings — that determines whether it gets watched. Use this to script a video, plan a series, fix retention or click-through problems, design thumbnail and title concepts, or turn written content into video. For a…
visual-content
Designs and directs the visual assets that carry content — carousels, infographics, quote graphics, diagrams, and social imagery — including the generation prompts where they are AI-produced. Use this to turn a written piece into a visual format, design a carousel or infographic, create social graphics, or fix visuals…
compose-creative
Core creative engine — turns a calendar post into finished images or video using 4 modes (anchor-compose, enhance-extend, style-referenced, pure-creative) with brand assets, AI generation, and human approval before credits are spent. Triggers on "/compose-creative", "generate the creative", "make the image for P07"…
c2pa-sign
Embed C2PA provenance manifests in AI-generated assets — the machine-readable AI disclosure EU AI Act Article 50 expects (enforceable since 2 Aug 2026), plus the human-approval record for the Article 50(4) exemption. Triggers on "/c2pa-sign", "sign this asset", "provenance", "content credentials", "AI disclosure"…
full-pipeline
Run the complete production pipeline end to end — parse the calendar, match assets, compose creative, adapt copy, build previews, run reviews, finalize delivery — with checkpoints between phases. Triggers on "/full-pipeline", "run the whole month", "produce the month", "end to end", "do everything", "full production…