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/shidoyu/scout/setupnpx skills add shidoyu/scout --skill setupgit clone --depth 1 https://github.com/shidoyu/scoutWrote 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/shidoyu/scout/setup)<a href="https://agentmods.dev/skills/shidoyu/scout/setup"><img src="https://agentmods.dev/badge/skills/shidoyu/scout/setup.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 | $0.00054 | $0.03849 |
| Opus 5 | $0.00027 | $0.01924 |
| Sonnet 5 | $0.00011 | $0.00770 |
| Haiku 4.5 | $0.00005 | $0.00385 |
Grade B, and why
setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 "$MCP_JSON" How it starts
The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scout:setup — Guided Configuration
Purpose
Walk the user through configuring scout's optional search and fetching tools via interactive dialogue. Each step explains what the tool adds and lets the user decide.
Core Principle
"scout already works. These options make it stronger. The user chooses."
Transparency Protocol
Every configuration change must be visible before it happens. This builds trust and lets the user understand what scout is doing to their environment.
-
Show the diff before writing — Before editing
.mcp.jsonor any config file, display the exact JSON block that will be added. Format: "Adding this to[file path]:" → fenced JSON block → then write. No extra confirmation needed — the step-level consent ("Install") already covers it. -
Echo commands before running — Before executing shell commands (e.g.,
npx playwright install chromium,claude mcp add ...,pip install ...), display the command first. Format: "Running:" → fenced command block → then execute. Do NOT ask for separate confirmation here — the step-level consent already covers it. -
State the footprint — For installs that add significant disk usage (e.g., Playwright ~200MB), state the approximate size before the user consents.
These rules apply to every step below. They do not add extra confirmation prompts — they make the existing prompts more informative.
Interaction Rules
- Respond in the user's language with dynamic equivalence — check the
locale:line from the pre-check output (e.g.ja_JP→ Japanese,es_ES→ Spanish,en_US→ English). ALL dialogue, explanations, step titles, and option descriptions MUST be in that language. Translate with dynamic equivalence (functional equivalence), not word-for-word. Prioritize natural, idiomatic phrasing that a native speaker would use — avoid translationese. Technical terms (API, MCP, Playwright, Context7, Jina Reader, Exa) stay in English. The English templates below are for content guidance only — NEVER output them as-is. - Frame each tool as an upgrade, not a missing piece
- Every step is skippable — do not ask why if the user declines
- State facts about what each tool adds, not what's lost without it
- No excessive celebration on completion. A simple confirmation is enough
- Never install or configure anything without explicit consent
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.
- 4d ago First seen · 312 lines · 54 tokens per session scan B 88f3a0c6f91b
setup is a skill published in the GitHub repository shidoyu/scout (3 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 3,849 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
web-access
Use this skill whenever the user needs to access information from the internet — searching for current information, fetching public web pages, browsing login-gated sites (微博/小红书/B站/飞书/Twitter), comparing products, researching topics, gathering documentation, or summarizing news. This skill orchestrates four…
pixelbrowse
Screenshot and visually read any web page or document using pixelshot. Use instead of fetching raw HTML when you need to see what a page looks like, read visual content (charts, diagrams, infographics), check layouts, or verify UI. Triggers: "look at this page", "screenshot", "what does this site look like", "check…
broken-link-checker
Scans a website to find broken links (404s, 500s). Crawls internal pages, identifies broken outbound links, and reports source pages for easy fixing. Use this when the user asks to "check for broken links", "find 404s", "audit my links", or "is my site healthy".
ddgs
Use when an agent needs to search the web, find images/news/videos/books, or extract content from a URL. Covers the ddgs Python library, CLI, and MCP server integration.
test-site
Tests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.
preview-screens
Use when the user wants to preview generated screens in a browser without starting Metro / a simulator — for example after /create-mobile-app finishes or after /edit-app regenerates a screen.