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 Razaib-khan/ForgeWeave --skill web-researchgit clone --depth 1 https://github.com/Razaib-khan/ForgeWeaveWrote 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/razaib-khan/forgeweave/web-research)<a href="https://agentmods.dev/skills/razaib-khan/forgeweave/web-research"><img src="https://agentmods.dev/badge/skills/razaib-khan/forgeweave/web-research.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 | $0.00021 | $0.00648 |
| Opus 5 | $0.00010 | $0.00324 |
| Sonnet 5 | $0.00004 | $0.00130 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
Web Research 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 7d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Research
Purpose
Fetch and extract content from live web pages using HTTP-based fetching (httpx + trafilatura) for standard pages and Playwright headless browser for JavaScript-rendered pages. Is the raw data acquisition layer for all research skills.
When to Use
- You need to fetch content from a specific URL
- A page requires JavaScript rendering to display its content
- You need to extract structured data from multiple pages
- Real-time information needs to be retrieved from the web
When Not to Use
- The user wants a summary of a topic they haven't specified URLs for
- The task is analyzing the local codebase
Inputs
| Input | Type | Required | Description |
|---|---|---|---|
url or urls |
string/array | Yes | URL(s) to fetch |
mode |
enum | No (default: auto) | auto, text, html, screenshot |
js_render |
boolean | No (default: false) | Whether to use Playwright |
Expected Outputs
| Output | Description |
|---|---|
| Clean text content | Extracted main content from the page |
| Code examples | Extracted code blocks if mode=auto |
| Screenshot | Full-page screenshot if mode=screenshot |
Exact Workflow Steps
- Try HTTP fetch first using
webfetch - If response is incomplete (<2000 chars) or empty, fall back to Playwright MCP tools:
browser_navigate— navigate to the URLbrowser_snapshot— get structured accessibility tree with element refsbrowser_console_messages— check for JS errors that may indicate rendering issues
- Extract clean text content and code blocks
- If requested, take a screenshot via
browser_take_screenshot(Playwright MCP)
Required Checks
- Content was successfully extracted
- Fallback to Playwright was attempted if HTTP fetch failed
- Rate limiting was respected (1s between requests to same domain)
Failure Modes
| Failure Condition | Response |
|---|---|
| HTTP 404 | Try with Playwright (some SPAs return 404 for JS-rendered content) |
| All methods fail | Report URL as unreachable |
| Content too large | Truncate and report |
What ships with it
2 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.
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.
- 7d ago First seen · 84 lines · 21 tokens per session scan A 969bb1fb7901
Web Research is a skill published in the GitHub repository Razaib-khan/ForgeWeave (1 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 648 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
browser-automation
Playwright-based browser automation patterns for autonomous web interaction.
c-browser
Headless browser automation — navigate pages, click elements, fill forms, take screenshots, scrape content using agent-browser or playwright-cli.
verify
Drive an engine app headlessly in a pty, record a video of the whole verification, and open a summary page (video + timeline + checks) with pixel open.
ketch
Research skill for ketch — a fast stateless CLI for web search, OSS code search, curated library docs, page scraping, and site crawling; an optional MCP server exists for operators who want it, but the CLI is the primary interface. Use when a question needs live sources: 'research X', 'what are people saying about Y'…
agent-browser
Headless browser automation CLI. Open, browse, interact with, and screenshot web pages. Use when: opening websites, browser-based login, web app testing, taking screenshots, UI verification.
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.