What is record-and-replay?

A recording tool that captures browser or desktop actions and turns a demonstrated workflow into a reusable agent skill.

Use it to record browser workflows with Playwright or native desktop workflows with mouse, keyboard, window, and screenshot events.

It removes the need to describe every step of a repeated task manually.

record-and-replay — Skill for Claude Code and Codex by ugarchance

Install

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.

Any agent

npx skills add ugarchance/record-and-replay-skill --skill record-and-replay-skill

Clone the repo

git clone --depth 1 https://github.com/ugarchance/record-and-replay-skill

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ugarchance/record-and-replay-skill/record-and-replay-skill/github.svg)](https://agentmods.dev/skills/ugarchance/record-and-replay-skill/record-and-replay-skill)

Your own site

<a href="https://agentmods.dev/skills/ugarchance/record-and-replay-skill/record-and-replay-skill"><img src="https://agentmods.dev/badge/skills/ugarchance/record-and-replay-skill/record-and-replay-skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ugarchance/record-and-replay-skill/record-and-replay-skill"><img src="https://agentmods.dev/badge/skills/ugarchance/record-and-replay-skill/record-and-replay-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,589 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00106	$0.03589
Opus 5.5	$0.00042	$0.01436
Sonnet 5.5	$0.00021	$0.00718
Haiku 4.5	$0.00011	$0.00359

Measured 2mo ago against content hash bb288f8965c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo ago.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/desktop-lite-recorder.py, scripts/desktop-permissions.py, scripts/desktop-record.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Record & Replay (browser + desktop)

Record & Replay lets an agent learn a user-demonstrated workflow and turn it into a reusable skill. Two modes:

Browser mode (default, richest evidence): a headed Playwright browser (system Google Chrome if available) records every user action into events.jsonl with multiple selector candidates, plus Playwright trace chunks (trace-NNN.zip). Works on macOS, Windows and Linux.
Desktop mode (native apps): a lightweight single-process recorder (pynput) captures global mouse/keyboard events, active-window changes and click-moment screenshots into desktop-events.jsonl + screens/ — Codex-parity (Codex records an event/context stream too, not video), ~1-3% CPU. Works on macOS, Windows and Linux (X11). See "Desktop recording" below.

Pick browser mode whenever the workflow is browser-only — its semantic selectors produce far better skills than desktop coordinates.

Setup (once)

cd ~/.agents/skills/record-and-replay
node setup.mjs      # npm install + (Chromium only if Chrome is missing) + self-tests
node install.mjs    # link into agent skill dirs (symlink on macOS/Linux, junction on Windows)

Installs the playwright npm package. Browsers are NOT downloaded when Google Chrome is installed (the recorder uses channel: 'chrome'); otherwise the script downloads Chromium. Both scripts are cross-platform (Node).

Recording Workflow

Start the recorder detached in the background only when the user is ready to begin. Always pass --name <slug> so the output directory is known up front:

cd ~/.agents/skills/record-and-replay
# macOS / Linux:
nohup node scripts/recorder.mjs --minutes 30 --name <slug> [--url <startUrl>] \
  > ~/.agents/recordings/recorder.log 2>&1 &
# Windows (PowerShell):
Start-Process node -WindowStyle Hidden -ArgumentList "scripts/recorder.mjs","--minutes","30","--name","<slug>"

Agents with a native background-run facility (e.g. Claude Code's Bash run_in_background) may use it instead. Outputs go to ~/.agents/recordings/<slug>/.

Read the full file on GitHub · 123 lines

Files

What ships with it

9 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.

Changes

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.

2mo ago First seen · 123 lines · 106 tokens per session scan A bb288f8965c8

Subscribe to this mod's changes

record-and-replay is a skill published in the GitHub repository ugarchance/record-and-replay-skill (49 stars, last pushed 3mo ago), licensed MIT. It adds 106 tokens to every session and 3,589 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 2026-08-30.

Browser automation Building agents Claude Code agent-skills codex computer-use opencode playwright

record-and-replay next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
record-and-replayugarchance/record-and-replay-skill	Skill	49	3mo ago	MIT	A	106	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
browsebrowserbase/stagehand	Skill	26k	yesterday	MIT	A	109	Claude Code
moli-webfetchlexmount/moli	Skill	23k	yesterday	Apache-2.0	A	90	Codex
moli-cdp-serverlexmount/moli	Skill	23k	yesterday	Apache-2.0	A	74	Codex
dev-browserSawyerHood/dev-browser	Skill	6.7k	3d ago	MIT	A	98	Claude Code, Codex
playwright-recordingdigitalsamba/claude-code-video-toolkit	Skill	2.5k	yesterday	MIT	A	53	Claude Code