Borrowing it
Nothing to install: this file belongs to suisya-systems/claude-org-ja. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/suisya-systems/claude-org-ja/main/.claude/skills/wsl-windows-chrome-screenshot/SKILL.mdgit clone --depth 1 https://github.com/suisya-systems/claude-org-jaWrote 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/suisya-systems/claude-org-ja/wsl-windows-chrome-screenshot)<a href="https://agentmods.dev/skills/suisya-systems/claude-org-ja/wsl-windows-chrome-screenshot"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/wsl-windows-chrome-screenshot/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/suisya-systems/claude-org-ja/wsl-windows-chrome-screenshot"><img src="https://agentmods.dev/badge/skills/suisya-systems/claude-org-ja/wsl-windows-chrome-screenshot.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 | $0.00142 | $0.03413 |
| Opus 5.5 | $0.00057 | $0.01365 |
| Sonnet 5.5 | $0.00028 | $0.00683 |
| Haiku 4.5 | $0.00014 | $0.00341 |
Grade A, and why
wsl-windows-chrome-screenshot 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`.worker-scratch/` に用意し、sandbox 内でプレビューが起動する(curl が 200)ことまで確かめ、 How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WSL から Windows Chrome で画面を撮る
Linux 側の Chrome は共有ライブラリ不足で起動しない環境なので、Windows 版 Chrome を
headless で使う。以下は繰り返し踏んだ手順を固定したもの(経緯と出典は
.claude/skills/wsl-windows-chrome-screenshot/references/rationale.md)。
どの失敗もエラーが原因を指さず、PNG が「撮れてしまう」ことが多い。
0. sandbox を外す撮影の実行は窓口が行う
§1 の dangerouslyDisableSandbox: true の呼び出しは、auto mode のワーカーでは分類器に
[Safety Bypass Flag] で拒否される(sandbox 内で Chrome を 1 回起動する probe も拒否)。
同じスクリプトは窓口が流して撮れている。よって役割を分ける。
- ワーカー: サーバ起動・撮影・停止を 1 本にまとめた撮影スクリプトを
.worker-scratch/に用意し、sandbox 内でプレビューが起動する(curl が 200)ことまで確かめ、 そのまま流せる 1 行のコマンドを窓口への報告に書く。sandbox 解除は自分で要求しない。 1 回でも拒否されたら再要求しない(繰り返すとロックアウトされる)。 - 窓口: スクリプトを読んでから sandbox 外で 1 回だけ流し、撮れた PNG が Chrome の 接続拒否画面(§2)でないことを確かめて、merge gate のページに載せる。
1. サーバ起動と撮影は 1 つの Bash 呼び出しに入れ、その呼び出しだけ sandbox を外す
sandbox は Bash 呼び出しごとに PID / network 名前空間を分けるため、
- 別呼び出しで起こしたサーバはその呼び出しの終了と同時に死ぬ(
setsidしても畳まれる。run_in_background: trueなら生きるが、次の呼び出しの curl からも Windows Chrome からも届かない) - Chrome 側も sandbox 内から叩くと
<3>WSL (N - ) ERROR: UtilConnectUnix:526: socket failed 1だけを出して PNG を 1 バイトも書かない(WSL interop の unix socket が bwrap に塞がれる。 エラー終了はしない)
よってサーバ起動・ヘルスチェック・撮影・停止をまとめた 1 呼び出しを
dangerouslyDisableSandbox: true で流す。build / verify / git は sandbox 内のままでよい。
CHROME="/mnt/c/Program Files/Google/Chrome/Application/chrome.exe"
SHOTS="$PWD/.worker-scratch/shots"; mkdir -p "$SHOTS"
UNC="$(wslpath -w "$SHOTS")" # Windows の Chrome に渡す \\wsl.localhost\... 形式の保存先
PORT=7361
shoot() { # shoot <name> <scheme 0=dark|1=light> <url>
"$CHROME" --headless=new --disable-gpu --hide-scrollbars \
--blink-settings=preferredColorScheme=$2 --window-size=2560,1440 \
--virtual-time-budget=4000 --screenshot="$UNC\\$1.png" "$3"
}
node .worker-scratch/preview-$PORT.mjs > .worker-scratch/preview.log 2>&1 &
SRV=$!
for i in $(seq 1 20); do curl -fsS -o /dev/null "http://127.0.0.1:$PORT/?lang=en" && break; sleep 1; done
shoot warmup 1 "http://127.0.0.1:$PORT/?lang=en" # 捨て撮り(§2)
shoot after-en 1 "http://127.0.0.1:$PORT/?lang=en"
shoot after-ja 1 "http://127.0.0.1:$PORT/?lang=ja"
kill $SRV
tail -5 .worker-scratch/preview.log
What ships with it
1 file 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.
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.
- 6d ago Changed · +4 lines f2f1af24b413
- 13d ago Changed · -19 lines · -83 tokens per session 53d9c3c9b1a1
- 1mo ago Changed · +22 lines ffcba969a62a
- 1mo ago First seen · 155 lines · 225 tokens per session scan A 378373148111
wsl-windows-chrome-screenshot is a skill published in the GitHub repository suisya-systems/claude-org-ja (5 stars, last pushed 5d ago), licensed MIT. It adds 142 tokens to every session and 3,413 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 2026-09-21.
Other skills, from other repositories
adaptive-anti-bot-web-scraping
Adaptive web scraping framework with anti-bot bypass and spider crawling.
agent-casino-gambling
Interact with MoltCasino - a 3D Vegas-style casino built for AI agents.
ai-powered-web-scraping-framework
AI-powered web scraping framework for extracting structured data from websites. Use when Codex needs to crawl, scrape, or extract data from web pages using AI-powered parsing, handle dynamic content, or work with complex HTML structures.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
takt
A workflow engine that runs a task through a sequence of steps defined in a YAML file, using separate coding agents for the work.
dingtalk_channel_connect
A browser-based setup guide for connecting a MateClaw assistant to DingTalk, a Chinese workplace messaging platform. It creates and configures a DingTalk application, then publishes the configuration.