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 instructions/digidai/website2markdown-skills/claude-mdgit clone --depth 1 https://github.com/Digidai/website2markdown-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/instructions/digidai/website2markdown-skills/claude-md)<a href="https://agentmods.dev/instructions/digidai/website2markdown-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/digidai/website2markdown-skills/claude-md.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 | $0.00505 | $0.00505 |
| Opus 5 | $0.00253 | $0.00253 |
| Sonnet 5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
website2markdown-skills CLAUDE.md 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `assets/recipes.md` — Copy-paste ready curl command recipes How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
website2markdown-skill
AgentSkills-compatible skill for converting web pages to Markdown via the md.genedai.me API.
Works with Claude Code, OpenClaw, and any AgentSkills-compatible agent.
Project Structure
SKILL.md— Core skill file (~250 lines, navigation hub) with AgentSkills frontmatterreferences/advanced-apis.md— Batch, Extract, DeepCrawl, Jobs API documentationreferences/platform-adapters.md— 21 platform adapters with URL patterns and examplesassets/recipes.md— Copy-paste ready curl command recipes
Development Guidelines
- SKILL.md must stay under 250 lines — it's the entry point, not the encyclopedia
- Detailed docs go in
references/; practical examples go inassets/ - All curl examples must use
curl -sand include?raw=true - Keep the Chinese platform coverage accurate — these are key differentiators
- SKILL.md frontmatter must follow AgentSkills spec; OpenClaw
metadatamust be single-line JSON - Test changes on both Claude Code and OpenClaw if possible
Deployment
# Claude Code
mkdir -p ~/.claude/skills/website2markdown
cp SKILL.md ~/.claude/skills/website2markdown/
cp -r references/ ~/.claude/skills/website2markdown/
cp -r assets/ ~/.claude/skills/website2markdown/
# OpenClaw
mkdir -p ~/.openclaw/skills/website2markdown
cp SKILL.md ~/.openclaw/skills/website2markdown/
cp -r references/ ~/.openclaw/skills/website2markdown/
cp -r assets/ ~/.openclaw/skills/website2markdown/
API Base URL
All API calls target https://md.genedai.me/.
Key Design Decisions
- SKILL.md acts as a routing hub: quick patterns inline, detailed docs via
Load references/... - Platform adapters are the main differentiator vs. plain Jina Reader
- The API auto-fallbacks: native → Readability+Turndown → Browser+Readability+Turndown
- Public endpoints need no auth; Batch/Extract/DeepCrawl/Jobs require
API_TOKEN - Follows AgentSkills open standard for cross-platform compatibility (Claude Code, OpenClaw, Cursor, etc.)
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 · 49 lines · 505 tokens per session scan A df5f2f7624c2
website2markdown-skills CLAUDE.md is an instructions file published in the GitHub repository Digidai/website2markdown-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 505 tokens to every session, about $0.0025 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 instructions, from other repositories
claude-chat-exporter CLAUDE.md
Instructions for agarwalvishal/claude-chat-exporter, covering claude.md, what this is, core design decision, how the export works and the install page & bookmarklet (docs/index.html).
snag AGENTS.md
AGENTS.md instructions for p3bot/snag, covering agents.md, project overview, setup commands, clone repository and install dependencies.
xiaohongshu-skill AGENTS.md
Instructions for DeliciousBuding/xiaohongshu-skill, covering agents.md, safety, execution, development and architecture.
unbrowser CLAUDE.md
Instructions for protostatis/unbrowser, covering unbrowser, why this exists, architecture (locked), stealth mode (native, on by default) and host functions exposed to js.
fanqie-publisher-skill AGENTS.md
Instructions for amm10090/fanqie-publisher-skill, covering fanqie-publisher-skill — codex cli agent adapter, read first, prerequisites, entry points and utf-8 / unicode safeguards.
fanqie-publisher-skill CLAUDE.md
Instructions for amm10090/fanqie-publisher-skill, covering fanqie-publisher-skill — claude code adapter, read first, entry points, prerequisites and utf-8 / unicode safeguards.