Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add edosulai/silenthand-cua --skill record-and-replaygit clone --depth 1 https://github.com/edosulai/silenthand-cuaWrote 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/edosulai/silenthand-cua/record-and-replay)<a href="https://agentmods.dev/skills/edosulai/silenthand-cua/record-and-replay"><img src="https://agentmods.dev/badge/skills/edosulai/silenthand-cua/record-and-replay/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/edosulai/silenthand-cua/record-and-replay"><img src="https://agentmods.dev/badge/skills/edosulai/silenthand-cua/record-and-replay.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 | $0.00032 | $0.00990 |
| Opus 5 | $0.00016 | $0.00495 |
| Sonnet 5 | $0.00006 | $0.00198 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
record-and-replay 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Record & Replay
Record & Replay lets ChatGPT learn a user-demonstrated macOS workflow and turn it into a reusable skill. Use it when the user asks you to watch them perform a task, record a workflow, or create or refine a skill from their demonstration.
Recording Workflow
- Use
event_stream_startonly when the user is ready to begin recording. - Starting asks the user to confirm before capture begins.
- After
event_stream_startsucceeds, do not sleep, poll, or wait in a loop for the user to finish. End your turn and ask the user to tell you when they are done recording and tell them what the time limit is on recording. - Use
event_stream_statusonly when the user asks for status or returns after recording; do not use it to poll while waiting. - Use
event_stream_stopwhen recording is complete. - When the user says they are done recording, read the returned
metadataPathandeventsPathfrom disk with normal filesystem tools and inspect the captured events before responding. - When the user says they cancelled recording, do not call
event_stream_stopagain or attempt to use the event stream. You may readsession.jsonif needed to confirm that itsendReasonisrecording_controls_cancelled; acknowledge the cancellation without creating or updating a skill. - Before creating or refining a skill, check whether the recording and the user's request clearly establish the reusable workflow, its intended outcome, and which demonstrated values should become skill inputs rather than fixed details. If any ambiguity would materially affect the skill, explain what is unclear, ask concise follow-up questions, and wait for the answers.
- Otherwise, if the recording contains enough information to identify a reusable workflow, create or refine a skill for that workflow by default even if the user did not explicitly ask for one; do not stop after providing a summary, replay plan, runbook, or suggestion to create one.
- The MCP server does not expose event-stream contents directly.
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 · 44 lines · 32 tokens per session scan A 9e25a9c0c7c4
record-and-replay is a skill published in the GitHub repository edosulai/silenthand-cua (0 stars, last pushed 10d ago), licensed MIT. It adds 32 tokens to every session and 990 once invoked, about $0.0002 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
cua-driver
Drive a native GUI app (macOS, Windows, Linux) via the cua-driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive, automate…
scarf-template-author
Scaffold a new Scarf project OR enrich an existing one after a Scarf "Upgrade Project" — dashboard, optional configuration schema, optional cron job, AGENTS.md, and (via the scarf-miniapp-author skill) a starter mini-app — from a short conversational interview. Output is immediately usable locally and cleanly…
scarf-miniapp-author
Author a Scarf mini-app — a small sandboxed web surface (HTML/CSS/JS) that renders inside a project's cockpit and talks to the bound Hermes session + project data through the versioned window.scarf bridge. Use to build a bespoke panel (a task board, an approval queue, a chart, a data table) for a project.
macos-harness
Control a whole Mac from one persistent Python session with screenshots, PID-targeted input, an animated virtual pointer, targeted Apple Accessibility, Apple Events, Browser Harness CDP, and filesystem access. Use for native, Electron, browser, dialog, file, or cross-app tasks without moving the physical cursor or…
host-computer-use
Beta desktop control through the connected A0 CLI host. Use for the user's host/local computer screenshots, screen inspection, menus, native app UI, OS-level clicking, scrolling, typing, or checking computeruseremote status. Use instead of linux-desktop for host/local machine control. Do not use for ordinary browser…
computer-basics
How this bot uses its pinned Orgo cloud computer (opt-in load).