use-workflow-pageshot

use-workflow-pageshot is a skill for Claude Code from thkt/dotclaude. It costs 78 tokens per session (884 once invoked), scanned A, original, MIT.

A pull-request helper that reads a preview link and test steps, then uses a browser to capture a screenshot or video of the tested page.

In plain words
What is it for?
Use it to capture one screenshot for a single test step, or a video for two or more steps, and return the saved file paths for attachment.
Why use it?
It removes the manual work of reproducing the steps and preparing visual proof for a GitHub pull request.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

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.

agentmods
npx agentmods add skills/thkt/dotclaude/use-workflow-pageshot
Any agent
npx skills add thkt/dotclaude --skill use-workflow-pageshot
Clone the repo
git clone --depth 1 https://github.com/thkt/dotclaude

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.

agentmods badge for use-workflow-pageshot

README.md
[![agentmods](https://agentmods.dev/badge/skills/thkt/dotclaude/use-workflow-pageshot.svg)](https://agentmods.dev/skills/thkt/dotclaude/use-workflow-pageshot)
Your own site
<a href="https://agentmods.dev/skills/thkt/dotclaude/use-workflow-pageshot"><img src="https://agentmods.dev/badge/skills/thkt/dotclaude/use-workflow-pageshot.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 884 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.00884
Opus 5 $0.00039 $0.00442
Sonnet 5 $0.00016 $0.00177
Haiku 4.5 $0.00008 $0.00088

Measured yesterday against content hash 3ffa7dcc559e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

use-workflow-pageshot 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 yesterday.

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.

.ja/skills/use-workflow-pageshot/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

use-workflow-pageshot

入力

PR 本文は /pr から文字列として渡される。下表のいずれかが欠落していれば、mode=failed reason=<欠落フィールド名> を返し、判断は /pr に任せる。

フィールド ソース
Preview URL PR 本文の冒頭にある Preview URL: <URL>
Steps PR 本文の ## How to Test セクション配下の番号付きリスト

ブラウザ engine

すべての agent-browser 呼び出しに --session pageshot --engine chrome を付ける。既定の lightpanda は screenshot でプレースホルダー PNG を返す。

モード選択

Steps の数 モード 成果物
1 screenshot step-01.png
2+ video capture.mp4

実行

ステップ アクション
1 出力ディレクトリを作成。.claude/workspace/pageshot/$(date +%Y%m%d-%H%M%S)/
2 agent-browser open {Preview URL}
3 モードに応じて Screenshot Flow または Video Flow を実行
4 成果物の絶対パスを stdout に出力

Screenshot Flow (1 step)

# コマンド
1 agent-browser snapshot でアクセシビリティツリーを取得
2 step に操作が含まれていれば agent-browser {click/type/fill/...} を実行
3 agent-browser screenshot --full {outdir}/step-01.png

Video Flow (2+ steps)

step 間に agent-browser wait 500 を挟む。各操作の前に snapshot を実行して要素を特定する。

# コマンド
1 agent-browser record start {outdir}/capture.webm
2 各 step について順に snapshot してから操作を実行
3 agent-browser record stop
4 ffmpeg -i {outdir}/capture.webm -vcodec libx264 {outdir}/capture.mp4

Read the full file on GitHub · 70 lines

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.

  1. yesterday Changed · -1 tokens per session 3ffa7dcc559e
  2. 6d ago First seen · 70 lines · 79 tokens per session scan A eed1fc362530

Subscribe to this mod's changes

use-workflow-pageshot is a skill published in the GitHub repository thkt/dotclaude (12 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 884 once invoked, about $0.0004 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 2026-08-30.