A pull-request walkthrough recorder that uses Playwright, a browser automation tool, to capture narrated videos and, when requested, before-and-after screenshots. A pull request is a proposed code change submitted for review.

Use it to record browser-based feature demonstrations or bug reproductions for a pull request.

It gives reviewers visual evidence of how a change behaves, including the original and fixed behavior for bug fixes.

record-pr — Skill for Claude Code by lucastamoios/skills

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 lucastamoios/skills --skill record-pr

Clone the repo

git clone --depth 1 https://github.com/lucastamoios/skills

Made for: Claude Code.

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/lucastamoios/skills/record-pr/github.svg)](https://agentmods.dev/skills/lucastamoios/skills/record-pr)

Your own site

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

Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,572 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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	$0.00153	$0.05572
Opus 5.5	$0.00061	$0.02229
Sonnet 5.5	$0.00031	$0.01114
Haiku 4.5	$0.00015	$0.00557

Measured 3d ago against content hash af4af3735a80, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

record-pr scanned grade A with 1 finding 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 3d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (lighthouse_files.py, test_lighthouse_files.py), 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Bash(git *), Bash(gh api *), Bash(docker *), Bash(just *), Bash(./dev_compose.sh *), Bash(curl *), Bash(lsof *), Bash(python3 *), Bash(ffmpeg *), Bash(brew *), Bash(uv *), Bash(.venv/bin/*), Read, Edit, Wr

skills/record-pr/SKILL.md · 266 lines

How it starts

The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Record PR walkthrough

Private configuration

For an ordinary invocation that needs personal defaults or integrations, read the installed skill-config skill and resolve the profile.<key> fields below. Load only context relevant to the request. For shell examples, set SKILL_CONFIG to the installed skill-config/scripts/config.py absolute path. The examples query the private profile at runtime; verify required fields before execution. Ask for required missing fields and skip unavailable optional integrations.

For a prepared worker packet, use only its declared access and supplied configuration. The coordinator resolves private defaults and passes the minimum required values or permitted resources. A worker must not load a machine-wide profile or unrelated context unless the packet explicitly permits it.

Produces a narrated Playwright walkthrough showing the change in action. For bug fixes, produces two videos - the bug repro (with the fix temporarily reverted) and the fix-applied case. Same scenario, same data, same camera, only the code changes. The output is intended to be embedded in the PR description via the /create-pr skill.

Video is the default and only output. When the user also asks for screenshots (prints, stills, a before/after image pair), additionally capture the before/after PNG pair described in Screenshots mode; it rides on the same script and recording passes, never on a separate ad-hoc flow.

When the arguments contain --lighthouse, skip everything else in this file and follow only Lighthouse mode at the end. The default behavior below does not apply to that mode, and that mode does not change the default behavior.

When to use

The diff touches frontend or workflow code and the change is interactive (multi-step, before/after comparison, bug repro). For a single static state, prefer the screenshot path in /create-pr instead.
The user explicitly asks for a walkthrough, demo, "show me the bug", a video, or before/after screenshots of a change.

Read the full file on GitHub · 266 lines

Files

What ships with it

2 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.

3d ago First seen · 266 lines · 153 tokens per session scan A af4af3735a80

Subscribe to this mod's changes

record-pr is a skill published in the GitHub repository lucastamoios/skills (0 stars, last pushed 4d ago), licensed MIT. It adds 153 tokens to every session and 5,572 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-05.

Browser automation Code review agent-skills codex developer-tools

record-pr next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
record-prlucastamoios/skills	Skill	0	4d ago	MIT	A	153	Claude Code
accessibility-cleanupchromium/chromium	Skill	25k	today	BSD-3-Clause	A	49	Claude Code, Codex
test-conversion-reviewerchromium/chromium	Skill	25k	today	BSD-3-Clause	A	37	Claude Code, Codex
remove-unused-includeschromium/chromium	Skill	25k	today	BSD-3-Clause	A	38	Claude Code, Codex
cl-link-from-hashchromium/chromium	Skill	25k	today	BSD-3-Clause	A	63	Claude Code, Codex
pr-screenshotsgithub/gh-aw	Skill	5.6k	today	MIT	A	17	Claude Code, Codex
sync-bridgechromium/chromium	Skill	25k	today	BSD-3-Clause	A	109	Claude Code, Codex

record-pr