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/appautomaton/markmaton/html-to-markdownnpx skills add appautomaton/markmaton --skill html-to-markdowngit clone --depth 1 https://github.com/appautomaton/markmatonWrote 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/appautomaton/markmaton/html-to-markdown)<a href="https://agentmods.dev/skills/appautomaton/markmaton/html-to-markdown"><img src="https://agentmods.dev/badge/skills/appautomaton/markmaton/html-to-markdown.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 | $0.00038 | $0.00587 |
| Opus 5 | $0.00019 | $0.00293 |
| Sonnet 5 | $0.00008 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
html-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 5d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTML to Markdown
Composes with
- Called by —
RECIPES.mdparse-jdrecipe (step 1). Any capture-a-web-page task in the workspace prefers this over built-inWebFetch. - Wraps — nodriver (CDP-based headless browser capture for JS-heavy pages, with Playwright Chromium discovery) and markmaton (HTML→Markdown with main-content extraction, metadata, and link/image inventory). See
references/integration-patterns.mdfor browser-vs-fetch guidance. - Outputs — JSON envelope by default (markdown body + metadata + links + images + quality signals). Use
--output-format markdownwhen only the raw Markdown body is needed.
Converts a URL or HTML into clean Markdown plus metadata, links, images, and quality signals.
From a URL
Capture the page and convert in one pipeline:
uv run --script scripts/capture_html.py <url> \
| uv run --script scripts/markmaton_convert.py --from-capture --output-format json
The capture script outputs a JSON envelope by default. --from-capture reads it and extracts html, url, final_url, and content_type automatically — no context lost, URL typed once.
- Add
--wait-selector <css>or--wait-text <string>to the capture step for pages that need a readiness signal. - Prefer a simple fetch over browser capture for static articles, wikis, and server-rendered docs.
From HTML
uv run --script scripts/markmaton_convert.py --html-file page.html \
--url <url> --output-format json
Or from stdin:
echo "$html" | uv run --script scripts/markmaton_convert.py --url <url>
Pass --url when available — it improves link resolution and canonical metadata.
Key defaults
- Output:
json. Use--output-format markdownfor raw Markdown only. - Main-content extraction: on. Use
--full-contentto disable. - Capture: always headless. Timeout
10s, override with--timeout. - Browser discovery: user's Chrome → user's Chromium → Playwright's Chromium.
References
Read only when needed:
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.
- 5d ago First seen · 62 lines · 38 tokens per session scan A 141f840c60aa
html-to-markdown is a skill published in the GitHub repository appautomaton/markmaton (5 stars, last pushed 21d ago), licensed MIT. It adds 38 tokens to every session and 587 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 2026-08-31.
Other skills, from other repositories
firecrawl-build
Integrate Firecrawl into application code whenever a product, agent, or workflow needs web data inside the app — web search, live search results, page scraping, structured extraction, or browser interaction. Use when building any feature that needs data from the web in code, even if the user does not mention Firecrawl…
firecrawl-build-scrape
Integrate Firecrawl /scrape into product code for single-page extraction. Use when an app already has a URL and needs markdown, HTML, links, screenshots, metadata, or structured page output. Prefer this skill over broader crawl patterns when the feature is page-level.
firecrawl-build-interact
Integrate Firecrawl /interact into product code for dynamic pages and browser actions after scraping. Use when a feature needs clicks, form fills, pagination, authentication-aware flows, or other multi-step interactions that plain /scrape cannot complete.
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…
youtube
Extract transcripts from YouTube videos via the YouTube caption system.
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.