Borrowing it
Nothing to install: this file belongs to WatermelonBros/reado. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/WatermelonBros/reado/main/.claude/skills/record-demo/SKILL.mdgit clone --depth 1 https://github.com/WatermelonBros/readoWrote 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/watermelonbros/reado/record-demo)<a href="https://agentmods.dev/skills/watermelonbros/reado/record-demo"><img src="https://agentmods.dev/badge/skills/watermelonbros/reado/record-demo/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/watermelonbros/reado/record-demo"><img src="https://agentmods.dev/badge/skills/watermelonbros/reado/record-demo.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 | $0.00090 | $0.01112 |
| Opus 5.5 | $0.00036 | $0.00445 |
| Sonnet 5.5 | $0.00018 | $0.00222 |
| Haiku 4.5 | $0.00009 | $0.00111 |
Grade A, and why
record-demo 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 29d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Record a Reado demo
Pieces (all in scripts/demo/):
| file | role |
|---|---|
run.mjs <scenario> [--record] |
runs a scenario against the dev app; with --record it also captures and exports |
record.sh start|stop|export <name> |
ffmpeg capture cropped to the Reado window → docs/media/<name>.mp4 (≤1920 wide) + .gif (960 wide) |
demo-kit.js |
injected into the webview: window.__demo = fake cursor (moveTo, click), human-paced type, caption pill say, hide |
scenarios/*.mjs |
one clip each: name, setup(app) (before recording), default(app) (the take) |
Prerequisites (check, don't assume)
ffmpegon PATH (brew install ffmpeg).- Screen Recording permission for the app hosting this session (the terminal / Reado).
Test:
ffmpeg -f avfoundation -i "Capture screen 0:none" -frames:v 1 /tmp/t.pngmust produce an image of the desktop, not black. - The dev build running with the UI driver, next to the installed app, on a throwaway fixture project — never the real repo (scenarios delete comments to get a clean take):
Launch it unsandboxed, in the background, from a short command. Wait until the bridge is up (bash scripts/bundle-cli.sh && npx tauri dev --config '{"identifier":"com.reado.dev"}' -- -- /path/to/fixture/src/cart.tslsof -nP -iTCP:1420 | grep -c com.apple≥ 2) before sending anything. Fixture: a git repo withsrc/cart.ts(the discount bug from the site's OG image),src/types.ts,src/discounts.ts(VIP: { percent: 1.2 }).
Workflow
- Rehearse without recording:
node scripts/demo/run.mjs scripts/demo/scenarios/<clip>.mjs. Fix selectors until it runs clean end to end. - Record:
node scripts/demo/run.mjs scripts/demo/scenarios/<clip>.mjs --record. The Reado dev window must stay in front and untouched for the whole take — the capture records the screen region, so anything on top of the window ends up in the video. Tell the user before a take. - Look at it before calling it done:
ffmpeg -i docs/media/<name>.mp4 -vf "fps=1/2,scale=800:-2,tile=2x3" -frames:v 1 /tmp/contact.png, then read the image.
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.
- 29d ago First seen · 61 lines · 90 tokens per session scan A 0d1e0d9b6300
record-demo is a skill published in the GitHub repository WatermelonBros/reado (30 stars, last pushed 8d ago), licensed MIT. It adds 90 tokens to every session and 1,112 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 2026-09-30.
Other skills, from other repositories
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…
cross-model-review
A second-opinion code review that asks a different AI model to independently inspect a change, then compares both reviews. It focuses on logic, security, consistency, and omissions.
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…