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/MobAI-App/desktop-recorder-skillnpx agentmods add skills/mobai-app/desktop-recorder-skill/desktop-recorderWrote 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/mobai-app/desktop-recorder-skill/desktop-recorder)<a href="https://agentmods.dev/skills/mobai-app/desktop-recorder-skill/desktop-recorder"><img src="https://agentmods.dev/badge/skills/mobai-app/desktop-recorder-skill/desktop-recorder/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/mobai-app/desktop-recorder-skill/desktop-recorder"><img src="https://agentmods.dev/badge/skills/mobai-app/desktop-recorder-skill/desktop-recorder.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 | $0.00126 | $0.03739 |
| Opus 5 | $0.00063 | $0.01869 |
| Sonnet 5 | $0.00025 | $0.00748 |
| Haiku 4.5 | $0.00013 | $0.00374 |
Grade A, and why
desktop-recorder 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 11d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Desktop Recorder
Built on deskagent (ScreenCaptureKit + AXPress + Vision OCR). The
agent never improvises during the final take - exploration is
unconstrained, the recording is a deterministic JSON-script replay.
Pre-recording checklist - ASK, don't pick silently
Use AskUserQuestion (or plain text) before recording. State defaults
explicitly so the user can shrug and accept.
| Decision | Default if user shrugs |
|---|---|
Background none / dark / light / color:RRGGBB / image:/path |
color:1a1a2e (dark navy). dark/light render as cached vertical gradients; image: covers the canvas. |
Layout for multi-source: auto / side-by-side / grid / stack |
auto |
| Padding between elements | 60 |
| Composition canvas | display native (or [1400, 1000] for the typical 1.4 AR) |
| Supersample on capture | 1 (device pixels). Bump to 2 for sharper playback when the editor will scale clips up |
| Cursor sprite | macOS system arrow with pointing-hand on click (deskagent cursor-png). Override via screenplay.highlights.cursor.{arrow,pointing,size} |
| Click ripple | Procedural soft expanding white ring. Override color/size/duration via screenplay.highlights.ripple.*, or supply your own .mov/APNG via ripple.sprite |
| Zoom follow_cursor | Enabled - camera tracks the synthetic cursor's eased path (shared with the sprite, no desync) |
| Final export resolution | display native (so QuickTime plays 1:1 on this machine) |
| Final quality | high (HEVC ~200 Mbps target) |
| State-verification level | preflight + fingerprint at dry-run boundary |
| Which apps may be driven | Whichever the user named; never silently click into others |
The 6 rules
1. Explore first
Tools allowed during exploration only:
deskagent list --json→ window pickingdeskagent inspect --window $ID→ element coords (AX + OCR)deskagent assert --window $ID --label X→ cheap yes/no probedeskagent screenshot --window $ID→ visual reference; on macOS 26/Tahoe hangs or capture failures, usenode scripts/record-screenshot.js --window $ID --out /tmp/shot.png- Trial
deskagent controlruns against the live UI
What ships with it
38 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.
- assets/examples/continuous-zoom-demo.json 1.5 KB
- assets/examples/notes-demo.json 2.3 KB
- assets/templates/captions-template.json 237 B
- assets/templates/copy-template.md 443 B
- references/deskagent.md 16 KB
- references/desktop.md 21 KB
- references/editing.md 14 KB
- references/timeline.md 4.0 KB
- references/web-driver.md 6.6 KB
- remotion-template/.gitignore 163 B
- remotion-template/package.json 406 B
- remotion-template/public/README.txt 98 B
- remotion-template/README.md 2.4 KB
- remotion-template/remotion.config.ts 81 B runs code
- remotion-template/src/bridge/Caption.tsx 1.6 KB
- remotion-template/src/bridge/ClickRipple.tsx 1.1 KB
- remotion-template/src/bridge/Cursor.tsx 883 B
- remotion-template/src/bridge/index.ts 344 B runs code
- remotion-template/src/bridge/loadRecording.ts 5.6 KB runs code
- remotion-template/src/bridge/RecordingCard.tsx 732 B
- remotion-template/src/bridge/RecordingStage.tsx 532 B
- remotion-template/src/Demo.tsx 3.2 KB
- remotion-template/src/index.ts 104 B runs code
- remotion-template/src/Root.tsx 678 B
- remotion-template/tsconfig.json 245 B
- scripts/drive-web.js 20 KB runs code
- scripts/export.js 7.5 KB runs code
- scripts/generate_copy.js 1.8 KB runs code
- scripts/lib/cursor-path.js 3.5 KB runs code
- scripts/lib/ffmpeg.js 3.9 KB runs code
- scripts/lib/filtergraph.js 470 B runs code
- scripts/lib/screenplay.js 18 KB runs code
- scripts/record-screenshot.js 6.3 KB runs code
- scripts/stages/captions.js 8.7 KB runs code
- scripts/stages/compose.js 5.6 KB runs code
- scripts/stages/highlights.js 15 KB runs code
- scripts/stages/speedups.js 4.9 KB runs code
- scripts/stages/zoom.js 11 KB runs code
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.
- 11d ago First seen · 262 lines · 126 tokens per session scan A bd58f2d8bb1c
desktop-recorder is a skill published in the GitHub repository MobAI-App/desktop-recorder-skill (19 stars, last pushed 2mo ago), licensed MIT. It adds 126 tokens to every session and 3,739 once invoked, about $0.0006 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 2026-08-30.
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.