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/huangyrcn/web-kit/browser-fetchnpx skills add huangyrcn/web-kit --skill browser-fetchgit clone --depth 1 https://github.com/huangyrcn/web-kitWrote 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/huangyrcn/web-kit/browser-fetch)<a href="https://agentmods.dev/skills/huangyrcn/web-kit/browser-fetch"><img src="https://agentmods.dev/badge/skills/huangyrcn/web-kit/browser-fetch.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 | $0.00152 | $0.01574 |
| Opus 5 | $0.00076 | $0.00787 |
| Sonnet 5 | $0.00030 | $0.00315 |
| Haiku 4.5 | $0.00015 | $0.00157 |
Grade A, and why
browser-fetch 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
## When to use browser-fetch vs curl/wget How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
browser-fetch
Fetch web content via a real Chrome browser connected over CDP. Executes JS,
bypasses anti-scraping, and reuses login cookies from the shared browser
profile. Two subcommands cover the two things an agent typically wants from a
URL: read its content (page) or save it as a file (file).
page vs file — which to use
| You want… | Use | Output |
|---|---|---|
| Read an article, doc page, or SPA's rendered content | page |
markdown (or json) |
| Save a PDF, zip, image, or other binary as a file | file |
raw file on disk |
| "What does this PDF say?" (extract text) | page |
markdown |
| "Download this PDF" (save the file) | file |
raw .pdf |
Rule of thumb: want the content → page; want the file → file.
How to invoke
Always use uv run --script — the script files may lack execute permission
after deployment.
page — render URL to markdown
# Save to file (recommended)
uv run --script ${SKILL_DIR}/scripts/page -O out.md "https://example.com"
# Output to stdout
uv run --script ${SKILL_DIR}/scripts/page -o md "https://example.com"
# Focused body content (less navigation/footer noise)
uv run --script ${SKILL_DIR}/scripts/page -o md-fit -O out.md "https://example.com"
# JSON (url, title, markdown, links)
uv run --script ${SKILL_DIR}/scripts/page -o json "https://example.com"
# Deep crawl (follow links)
uv run --script ${SKILL_DIR}/scripts/page --deep-crawl bfs --max-depth 20 -O out.md "https://..."
# Bypass cache
uv run --script ${SKILL_DIR}/scripts/page -bc -O out.md "https://example.com"
file — download URL to a raw file
uv run --script ${SKILL_DIR}/scripts/file <url> [output_file]
uv run --script ${SKILL_DIR}/scripts/file <url> output.pdf
uv run --script ${SKILL_DIR}/scripts/file <url> output.pdf --interactive
page — output formats
| Format | Flag | Content |
|---|---|---|
md |
-o md |
Full page markdown (default) |
md-fit |
-o md-fit |
Focused body content, less navigation noise |
json |
-o json |
JSON with url, title, markdown, links |
all |
-o all |
Full JSON dump |
What ships with it
4 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.
- 4d ago First seen · 162 lines · 152 tokens per session scan A 848a6e98f6ec
browser-fetch is a skill published in the GitHub repository huangyrcn/web-kit (5 stars, last pushed 2mo ago), licensed MIT. It adds 152 tokens to every session and 1,574 once invoked, about $0.0008 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
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…