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/agents-mdgit clone --depth 1 https://github.com/Digidai/website2markdownWhat 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 | $0.00220 | $0.00220 |
| Opus 5 | $0.00110 | $0.00110 |
| Sonnet 5 | $0.00044 | $0.00044 |
| Haiku 4.5 | $0.00022 | $0.00022 |
Grade A, and why
website2markdown AGENTS.md 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 2d 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.
This is a copy
89% identical to vibecop CLAUDE.md — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
md-genedai (website2markdown)
URL-to-Markdown Cloudflare Worker with Chinese platform adapters.
Skill routing
When the user's request matches an available skill, ALWAYS invoke it using the Skill tool as your FIRST action. Do NOT answer directly, do NOT use other tools first. The skill has specialized workflows that produce better results than ad-hoc answers.
Key routing rules:
- Product ideas, "is this worth building", brainstorming → invoke office-hours
- Bugs, errors, "why is this broken", 500 errors → invoke investigate
- Ship, deploy, push, create PR → invoke ship
- QA, test the site, find bugs → invoke qa
- Code review, check my diff → invoke review
- Update docs after shipping → invoke document-release
- Weekly retro → invoke retro
- Design system, brand → invoke design-consultation
- Visual audit, design polish → invoke design-review
- Architecture review → invoke plan-eng-review
- Save progress, checkpoint, resume → invoke checkpoint
- Code quality, health check → invoke health
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.
- 2d ago First seen · 24 lines · 220 tokens per session scan A 5540b451ff5e
website2markdown AGENTS.md is an instructions file published in the GitHub repository Digidai/website2markdown (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 220 tokens to every session, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to vibecop CLAUDE.md, differing in 4 lines, and is treated as a copy.
Other instructions, from other repositories
mdread CLAUDE.md
Instructions for techjewel/mdread, covering claude.md, what this is, commands, architecture and styles (scss).
behold AGENTS.md
Instructions for kitlangton/behold, covering behold, architecture, invariants, agent surface and markdown.
FounderOS CLAUDE.md
Instructions for ARCASSystems/FounderOS, covering founder os - claude code plugin, what this is, positioning non-negotiables, quick start and updates.
FounderOS AGENTS.md
Instructions for ARCASSystems/FounderOS, covering founderos - agent instructions, read first, joining the operator's team, writing and commits and built by.
context CLAUDE.md
Claude Code instructions for Supa-Media/context, covering agent instructions — context, non-negotiables, 1. the customer owns the storage, 2. tenancy is bucket-level, never prefix-level and 3. plain files stay canonical.
FounderOS GEMINI.md
Instructions for ARCASSystems/FounderOS, covering founderos - gemini cli context, read first, gemini-specific operating notes, writing and commits and built by.