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 agentmods add skills/zookanalytics/gc-toolkit/demo-capturenpx skills add zookanalytics/gc-toolkit --skill demo-capturegit clone --depth 1 https://github.com/zookanalytics/gc-toolkitWrote 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/zookanalytics/gc-toolkit/demo-capture)<a href="https://agentmods.dev/skills/zookanalytics/gc-toolkit/demo-capture"><img src="https://agentmods.dev/badge/skills/zookanalytics/gc-toolkit/demo-capture.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.03220 |
| Opus 5 | $0.00011 | $0.01610 |
| Sonnet 5 | $0.00004 | $0.00644 |
| Haiku 4.5 | $0.00002 | $0.00322 |
Grade A, and why
demo:capture 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 5d 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Demo Capture (Playwright MCP)
Capture a narrated demo video that proves features work, not just shows screens where features live.
Input
You MUST receive a complete markdown demo script. Do not invent or improvise a demo — if no script is provided, ask the caller for one.
Demo Script Format
The script must contain these sections:
# Demo: <title>— title, used in the output filename**Start:** <url>— URL where the demo begins**Auth:** yes|no— whether authenticated session is needed (default: yes). Auth is handled automatically by the Playwright MCP server.## Steps— ordered list where each item has:- Bold heading = narration text (burned into video overlay)
- Body text = action description for the executor
_Prove:_= what the frame must demonstrate to pass (REQUIRED)_Fail if:_= conditions that mean the frame failed its purpose (REQUIRED)
## Scrutiny(optional) — items to actively investigate. These make demos critical rather than superficial.
Script Validation (Before Execution)
The caller is responsible for validating the script before dispatching. For each step, the caller must verify:
- The
_Prove:_criterion is achievable with the current app state and data - The navigation path will reach a page state that satisfies the proof
- Seed data or existing documents contain the necessary content
Example of a bad script step (caught by validation):
3. **Word-level diff highlighting**
Open Compare to Original on the blog post document.
_Prove:_ Colored spans within a line show which words changed
_Fail if:_ All changes are pure additions with no modified lines
If the document was created from empty, Compare to Original will only show additions. The caller should check this before writing the step — navigate to the page, inspect the data, and choose a path that exercises the feature (e.g., Version History diffs between intermediate versions where text was modified).
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.
- 5d ago First seen · 324 lines · 22 tokens per session scan A f516e0b1d49f
demo:capture is a skill published in the GitHub repository zookanalytics/gc-toolkit (5 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 3,220 once invoked, about $0.0001 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
dingtalk_channel_connect
使用可见浏览器自动完成 MateClaw 钉钉渠道接入。遇到登录页必须暂停等待用户手动登录后继续。.
browser_cdp
通过 Chrome DevTools Protocol (CDP) 连接已运行的浏览器,或扫描本机 CDP 端口,用于远程调试与多工具共享浏览器实例。.
browser_visible
以可见模式启动真实浏览器窗口,适用于演示、调试或需要人工参与的场景。控制 headed/cdpPort 等启动参数。.
shogun-screenshot
スクリーンショットの取得・加工を行う。ローカルスクショから最新画像を取得、 PlaywrightでWebページをキャプチャ、画像のトリミング・リサイズ、機微情報を黒塗りマスキング。 記事執筆、レポート作成、UI確認、画像加工時に起動。 「スクショ」「スクリーンショット」「画面キャプチャ」「最新のスクショ」「画像加工」「トリミング」「マスク」「写メ」「写メ撮った」「スクショ撮った」で起動。 Do NOT use for: 画像生成(shogun-imagegenを使え)。.
browser-doctor
Read-only health check on browser-control setup. Verifies browser binary, Playwright MCP Bridge extension presence, token file mode/contents, AIWG MCP registration, provider config injection, and optional workspace allow-list. Outputs pass/fail per check with remediation commands.
browser_scripts
Visual browser automation script editor & manager for TubeCLI.