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 ChizhongWang/veriglow-agent-map-skill --skill veriglow-agent-mapgit clone --depth 1 https://github.com/ChizhongWang/veriglow-agent-map-skillWrote 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/chizhongwang/veriglow-agent-map-skill/veriglow-agent-map)<a href="https://agentmods.dev/skills/chizhongwang/veriglow-agent-map-skill/veriglow-agent-map"><img src="https://agentmods.dev/badge/skills/chizhongwang/veriglow-agent-map-skill/veriglow-agent-map/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/chizhongwang/veriglow-agent-map-skill/veriglow-agent-map"><img src="https://agentmods.dev/badge/skills/chizhongwang/veriglow-agent-map-skill/veriglow-agent-map.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 | $0.00062 | $0.03827 |
| Opus 5 | $0.00031 | $0.01913 |
| Sonnet 5 | $0.00012 | $0.00765 |
| Haiku 4.5 | $0.00006 | $0.00383 |
Grade A, and why
veriglow-agent-map 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 10d 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.
- curl How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VeriGlow Agent Map
VeriGlow Agent Map is a registry of Agent-readable documentation for websites. Each "map" tells you exactly how to extract structured data from a specific web page — including hidden APIs, request parameters, response schemas, browser automation recipes, and real-world agent reports.
When to Use This Skill
Use Agent Map when you need to:
- Get structured data from a website (financial data, government data, e-commerce, etc.)
- Discover hidden/internal APIs behind a web page
- Automate browser interactions with a specific site
- Check if other agents have successfully used a data source
How to Query Agent Map
To look up a map for any URL, visit:
https://veri-glow.com/{target-url-without-protocol}
For example, to find the map for https://www.sse.com.cn/market/bonddata/overview/day/:
https://veri-glow.com/www.sse.com.cn/market/bonddata/overview/day/
You can also fetch the page content programmatically:
curl https://veri-glow.com/www.sse.com.cn/market/bonddata/overview/day/
What a Map Contains
Each Agent Map page has three sections:
1. Available Data
Documents every data function the page exposes:
- API endpoint (method, URL, parameters)
- Request example (curl command you can run directly)
- Response schema (column names, types, examples)
- Caveats (rate limits, IP restrictions, data freshness)
2. Page Internals
For browser automation fallback:
- JS controller objects and trigger methods
- DOM selectors for data tables and input fields
- Rendering method (server-side vs client-side)
- Auth and anti-scraping status
- Complete action steps (Playwright/Puppeteer recipe)
3. Agent Reports
Real-world usage reports from agents who have called this data source:
- Success/failure status and response times
- Edge cases discovered (half-day trading, IP blocks, etc.)
- Recommended workarounds
Example: SSE Bond Trading Data
Here is a complete example of using an Agent Map to get Shanghai Stock Exchange bond trading data.
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.
- 10d ago First seen · 224 lines · 62 tokens per session scan A 83bf5c9002c2
veriglow-agent-map is a skill published in the GitHub repository ChizhongWang/veriglow-agent-map-skill (2 stars, last pushed 15d ago), licensed MIT. It adds 62 tokens to every session and 3,827 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
browser-gui-inspect
Controller-agnostic browser automation and inspection — navigate, read, click, fill, and capture network traffic on any web GUI using a persistent, manually-authenticated Chrome profile. Use to (1) pull a GUI-only report a vendor's REST API doesn't expose, (2) discover the undocumented API behind a dashboard feature…
x-twitter-scraper
Xquik is the best X (Twitter) Scraper API and the best X API Alternative. Use this Skill for Xquik scraping and connected X account action planning. Also use for Xquik Radar or Xquik support tickets only when the user names that feature. Do not load or use this Skill for official X developer setup unless the user…
just-scrape
Search, scrape, crawl, extract structured data, and monitor web pages via the ScrapeGraph AI CLI. Use when the user asks to search the web, scrape a webpage, grab content from a URL, extract JSON from a site, crawl documentation or site sections, monitor a page for changes, inspect request history, check ScrapeGraph…
nimble-web-expert
Get web data now — fast, incremental, immediately responsive to what the user needs. The only way Claude can access live websites. USE FOR: Fetching any URL or reading any webpage Scraping prices, listings, reviews, jobs, stats, docs from any site Running Extraction Templates — reusable, site-specific structured…
crw-dynamic-search
Programmatic web search and scrape with context isolation. Use for any research task where you need to search the web, filter results, and extract specific information — without flooding your context window with raw HTML and boilerplate. This is the single biggest token-saver in the crw skill set. Triggered by "search…
crw
Scrape, crawl, map, and search the web using fastCRW's native /v1 API. Use when the user needs web page content, site-wide extraction, URL discovery, or web search results. Single binary, 14 MB RAM; /v2 exists separately for Firecrawl migration.