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 tranfu-labs/tranfu-skills --skill url-to-markdowngit clone --depth 1 https://github.com/tranfu-labs/tranfu-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/tranfu-labs/tranfu-skills/url-to-markdown)<a href="https://agentmods.dev/skills/tranfu-labs/tranfu-skills/url-to-markdown"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/url-to-markdown/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/tranfu-labs/tranfu-skills/url-to-markdown"><img src="https://agentmods.dev/badge/skills/tranfu-labs/tranfu-skills/url-to-markdown.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 | $0.00044 | $0.02787 |
| Opus 5 | $0.00022 | $0.01393 |
| Sonnet 5 | $0.00009 | $0.00557 |
| Haiku 4.5 | $0.00004 | $0.00279 |
Grade A, and why
url-to-markdown 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 9d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
URL to Markdown
Fetch a URL through the bundled url-to-markdown CLI (Chrome CDP + site-specific adapters) and convert the rendered page to clean Markdown or JSON.
Scope Guard
- Require one HTTP or HTTPS URL.
- Capture only pages that require no login or manual verification. NEVER ask the user to sign in, solve a CAPTCHA, or operate the browser.
- Preserve the source content; do not summarize, rewrite, translate, or publish it.
- Use the built-in
x,youtube,hn, orgenericadapter. Do not invent site-specific extraction logic outside the bundled CLI. - Write only the requested capture, optional media, debug artifacts, and the preference file created through the required first-time setup.
- Treat
--cdp-urland Chrome profile contents as user-supplied browser state. NEVER export, restore, or manage authentication state.
Guarded Procedure
CREATE A TODO LIST FOR THE TASKS BELOW, with one TODO for each numbered stage, then execute stages 1–7 in order.
- Resolve
{baseDir}, the bundled reader path, and the preference-file candidates. If a bundled Skill resource is missing, stop and report its path. - Resolve preferences using Preferences. If no
EXTEND.mdexists, run the blocking first-time setup, save the selected values, then resume this procedure. - Validate the URL and construct a non-conflicting output path using Output Path Generation. If the URL is missing or is not HTTP/HTTPS, stop and request a valid URL.
- Resolve Bun, Chrome, and CLI dependencies as specified in CLI Setup. Select the adapter automatically unless the user explicitly requests a supported adapter. Apply explicit CLI arguments before preferences, and preferences before defaults.
- Run the non-interactive capture with
--quietwhen saving via--output, then immediately apply the Agent Quality Gate. If the CLI reports a login or verification wall, or the saved content is a login, CAPTCHA, shell, or low-quality result, delete any unusable capture, report that the page is unsupported, and stop. NEVER retry through login or manual browser interaction. - Apply the media workflow in references/adapters.md. If preferences say
ask, prompt only when the saved Markdown contains remote image or video URLs, including a FrontmattercoverImage. - Confirm that the saved title and body match the target page, then report the output path, selected adapter, media result, and any unverified limitation. Produce that capture report and end.
What ships with it
51 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.
- agents/openai.yaml 261 B
- assets/icon.png 645 B
- assets/icon.svg 507 B
- LICENSE 1.0 KB
- NOTICE 1.5 KB
- README.md 2.8 KB
- README.zh.md 2.6 KB
- references/adapters.md 3.5 KB
- references/config/first-time-setup.md 2.7 KB
- references/quality-gate.md 1.8 KB
- scripts/bun.lock 34 KB
- scripts/lib/adapters/generic/index.ts 2.3 KB runs code
- scripts/lib/adapters/hn/index.ts 10 KB runs code
- scripts/lib/adapters/index.ts 834 B runs code
- scripts/lib/adapters/types.ts 1.1 KB runs code
- scripts/lib/adapters/x/article.ts 12 KB runs code
- scripts/lib/adapters/x/index.ts 2.4 KB runs code
- scripts/lib/adapters/x/match.ts 296 B runs code
- scripts/lib/adapters/x/payloads.ts 1.6 KB runs code
- scripts/lib/adapters/x/shared.ts 13 KB runs code
- scripts/lib/adapters/x/single.ts 2.5 KB runs code
- scripts/lib/adapters/x/thread-loader.ts 8.9 KB runs code
- scripts/lib/adapters/x/thread.ts 9.0 KB runs code
- scripts/lib/adapters/x/types.ts 600 B runs code
- scripts/lib/adapters/youtube/index.ts 898 B runs code
- scripts/lib/adapters/youtube/transcript.ts 13 KB runs code
- scripts/lib/adapters/youtube/utils.ts 6.4 KB runs code
- scripts/lib/browser/access-blocks.ts 5.1 KB runs code
- scripts/lib/browser/cdp-client.ts 6.1 KB runs code
- scripts/lib/browser/chrome-launcher.ts 5.7 KB runs code
- scripts/lib/browser/network-journal.ts 7.0 KB runs code
- scripts/lib/browser/page-snapshot.ts 3.3 KB runs code
- scripts/lib/browser/profile.ts 5.6 KB runs code
- scripts/lib/browser/session.ts 3.3 KB runs code
- scripts/lib/cli.ts 4.7 KB runs code
- scripts/lib/commands/convert.ts 7.2 KB runs code
- scripts/lib/extract/document.ts 846 B runs code
- scripts/lib/extract/html-cleaner.ts 11 KB runs code
- scripts/lib/extract/html-extractor.ts 2.2 KB runs code
- scripts/lib/extract/html-to-markdown.ts 21 KB runs code
- scripts/lib/extract/markdown-renderer.ts 4.6 KB runs code
- scripts/lib/media/default-downloader.ts 5.1 KB runs code
- scripts/lib/media/markdown-media.ts 13 KB runs code
- scripts/lib/media/media-utils.ts 6.1 KB runs code
- scripts/lib/media/types.ts 710 B runs code
- scripts/lib/types/defuddle-node.d.ts 605 B runs code
- scripts/lib/types/shims.d.ts 422 B runs code
- scripts/lib/utils/logger.ts 644 B runs code
- scripts/lib/utils/url.ts 299 B runs code
- scripts/package.json 595 B
- scripts/url-to-markdown 122 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.
- 9d ago First seen · 214 lines · 44 tokens per session scan A 28fb518f79aa
url-to-markdown is a skill published in the GitHub repository tranfu-labs/tranfu-skills (2 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 2,787 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
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.
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.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
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…