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/Mazalucas/El-DT-Lightweight-Armynpx agentmods add skills/mazalucas/el-dt-lightweight-army/recordlyWrote 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/mazalucas/el-dt-lightweight-army/recordly)<a href="https://agentmods.dev/skills/mazalucas/el-dt-lightweight-army/recordly"><img src="https://agentmods.dev/badge/skills/mazalucas/el-dt-lightweight-army/recordly/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/mazalucas/el-dt-lightweight-army/recordly"><img src="https://agentmods.dev/badge/skills/mazalucas/el-dt-lightweight-army/recordly.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 | $0.00088 | $0.00562 |
| Opus 5.5 | $0.00035 | $0.00225 |
| Sonnet 5.5 | $0.00018 | $0.00112 |
| Haiku 4.5 | $0.00009 | $0.00056 |
Grade A, and why
recordly 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 1mo 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.
What it actually says
/recordly
Demo del producto real. Recordly graba la ventana y la pule. El DT no copia esa app.
/recordingly es el mismo carril.
Cuándo es este carril
Hay que mostrar la app corriendo: clics, cursor, un flujo, un GIF para el README. Si el pedido es un clip de 15–25 s armado desde el código, una plantilla React o footage generado, volvé a tools/video/ROUTING.md.
Un /recordly explícito confirma este carril. Si el brief no entra, decilo en una línea y nombrá el carril que sí entra.
App, sin vendorear
Si en macOS no existe /Applications/Recordly.app:
./tools/video/install-recordly.sh
Eso baja el instalador oficial a output/.cache/recordly/ (gitignored). No clones el repo. No hagas npm install en el DT. La persona abre el dmg y mueve Recordly a Aplicaciones. En macOS 14+ hace falta el permiso de grabación de pantalla.
Producir
- Escribí una lista de tomas: ventana o URL local, pasos a clickear, qué decir, MP4 o GIF, y relación de aspecto.
- Dejala en el chat y, si hace falta archivo, en
output/recordly/tomas.md(gitignored). - La persona graba y exporta. El agente no aprieta record ni reescribe el flujo en Playwright, Remotion o
/brag. - Si después piden títulos, variantes o un template sobre esa toma, esa segunda pieza sale por el carril de
tools/video/ROUTING.md.
Entrega
Lista de tomas, si la app ya estaba instalada o la ruta del instalador en caché, y dónde quedó el export cuando la persona lo tenga. Si la descarga falla, mostrá el error y el link al release oficial.
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.
- 1mo ago First seen · 43 lines · 88 tokens per session scan A 97f55659ac17
recordly is a skill published in the GitHub repository Mazalucas/El-DT-Lightweight-Army (4 stars, last pushed yesterday), licensed MIT. It adds 88 tokens to every session and 562 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 2026-09-24.
Other skills, from other repositories
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(usecloud=True)), Playwright, Puppeteer or any CDP client.
x402
Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…
computer-use
Drives the GUI of a visible local app window through orca computer: accessibility tree, clicks, typing, menus, dialogs, and screenshots in native apps and external browser windows (Chrome, Edge, Safari) or webviews. Prefer a programmatic path (shell, filesystem, git, HTTP, existing CLIs) whenever it can complete the…
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
stealth-browser-mcp
Use this skill when operating stealth-browser-mcp from an AI agent or MCP client for browser automation, page inspection, element interaction, screenshots, file uploads, CDP commands, network debugging, cookies/storage, stealth setup, or reliable multi-step browser workflows. It provides the correct tool order, state…
browser-cdp
Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions. Covers: launching Chrome in debug mode, opening URLs, waiting for page load, evaluating JavaScript, taking snapshots, and extracting auth tokens. Trigger phrases: browser automation, CDP…