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 skills add yaojingang/yao-geo-skills --skill yao-doubao-crawlergit clone --depth 1 https://github.com/yaojingang/yao-geo-skillsWrote 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/yaojingang/yao-geo-skills/yao-doubao-crawler)<a href="https://agentmods.dev/skills/yaojingang/yao-geo-skills/yao-doubao-crawler"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-geo-skills/yao-doubao-crawler/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/yaojingang/yao-geo-skills/yao-doubao-crawler"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-geo-skills/yao-doubao-crawler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00085 | $0.00426 |
| Opus 5 | $0.00043 | $0.00213 |
| Sonnet 5 | $0.00017 | $0.00085 |
| Haiku 4.5 | $0.00009 | $0.00043 |
Grade A, and why
yao-doubao-crawler 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 13d 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.
What it actually says
Yao Doubao Crawler
Inputs
Collect with keywords/questions, repeat count, backend (web or mobile), connection fields, and output dir. Add target entity + entity type for standard diagnosis. Without a target, generate exploratory output and label inferred candidates as heuristic.
Workflow
- Read
references/user-setup-and-usage.md,references/doubao-crawl-workflow.md, andreferences/report-contract.md. - For Android/Appium, also read
references/mobile-appium-workflow.mdand runpython3 scripts/doubao_mobile_crawl.py preflight .... - Stage 1 web: run
scripts/doubao_batch_crawl.mjs. - Stage 1 mobile: run
scripts/doubao_mobile_crawl.py batch; use--fresh-chat --require-fresh-chatwhen samples must start in separate Doubao app conversations. - Stage 2: run
scripts/analyze_doubao_results.pyon the compatible crawl JSON. - Use
evals/andtemplates/for packaging checks and collection briefs. - Return crawl JSON,
summary.json, structured Markdown/Excel, HTML report, screenshots/XML for mobile, failed logs, and mobile search-material evidence when present.
Honest Boundaries
- Do not bypass login, CAPTCHA, risk controls, hidden APIs, network traffic, or app storage.
- Android/Appium is low-frequency visible UI evidence capture.
- Probability and competitor metrics are repeated-sample estimates; review aliases before external use.
- Preserve raw answers, references, URLs, screenshots/XML, and logs.
What ships with it
29 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.
- .gitignore 122 B
- .skillignore 122 B
- agents/interface.yaml 1.7 KB
- evals/expected_artifacts.json 1.2 KB
- evals/trigger_cases.json 1.2 KB
- examples/README.md 405 B
- fixtures/sample-doubao-crawl.json 7.4 KB
- fixtures/sample-doubao-mobile-crawl.json 8.4 KB
- manifest.json 3.2 KB
- README.md 9.1 KB
- references/doubao-crawl-workflow.md 5.6 KB
- references/mobile-appium-workflow.md 8.5 KB
- references/report-contract.md 18 KB
- references/user-setup-and-usage.md 13 KB
- reports/mobile-beijing-study-abroad-20260703-5x-30s-fresh/report.html 108 KB
- reports/mobile-beijing-study-abroad-20260703-5x-30s-fresh/structured-data.md 98 KB
- reports/mobile-beijing-study-abroad-20260703-5x-30s-fresh/structured-data.xlsx 57 KB
- reports/mobile-beijing-study-abroad-20260703-5x-30s-fresh/summary.json 343 KB
- requirements-mobile.txt 28 B
- scripts/analyze_doubao_results.py 207 KB runs code
- scripts/doubao_batch_crawl.mjs 20 KB runs code
- scripts/doubao_browser_crawl.mjs 14 KB runs code
- scripts/doubao_mobile_crawl.py 86 KB runs code
- scripts/preflight.mjs 12 KB runs code
- scripts/run-tests.sh 927 B runs code
- scripts/test_doubao_browser_crawl.mjs 5.7 KB runs code
- scripts/test_entity_recognition.py 5.7 KB runs code
- scripts/test_mobile_extraction.py 15 KB runs code
- templates/brief-template.md 491 B
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.
- 13d ago First seen · 28 lines · 85 tokens per session scan A ed4051a8945e
yao-doubao-crawler is a skill published in the GitHub repository yaojingang/yao-geo-skills (742 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 426 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.
Other skills, from other repositories
agentql-automation
Automate Agentql tasks via Rube MCP (Composio). Always search tools first for current schemas.
anchor-browser-automation
Automate Anchor Browser tasks via Rube MCP (Composio). Always search tools first for current schemas.
defuddle
Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for URLs ending in .md — those are already…
agentcookie-install
Install agentcookie on a Mac source and a Linux or Mac sink so Chrome cookies sync continuously over Tailscale. Use when the user says "install agentcookie", "set up cookie sync", "share my Chrome sessions with my agent box", or "make my agent log in as me".
tauri-mcp-cli
Use the Tauri MCP CLI to start and recover driver sessions, automate Tauri webviews, capture UI state, debug IPC, and work with mobile or remote devices. Use whenever an agent needs to operate a Tauri v2 app from terminal commands.
browser-automation
A browser-automation workflow that detects the terminal environment and chooses a browser control tool. It supports opening pages, taking snapshots, clicking, filling fields, and other checks.