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/vin-spiegel/htmldrop/agents-mdgit clone --depth 1 https://github.com/vin-spiegel/htmldropWrote 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/vin-spiegel/htmldrop/agents-md)<a href="https://agentmods.dev/instructions/vin-spiegel/htmldrop/agents-md"><img src="https://agentmods.dev/badge/instructions/vin-spiegel/htmldrop/agents-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 | $0.01107 | $0.01107 |
| Opus 5 | $0.00553 | $0.00553 |
| Sonnet 5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
htmldrop AGENTS.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.
curl -X POST https://htmldrop.link/publish \ How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
htmldrop — MCP server for publishing HTML
This is the htmldrop MCP server (htmldrop.link). It lets an agent publish an HTML artifact and receive a public URL. The MCP tool name is publish_html.
Service endpoints
| Endpoint | URL |
|---|---|
| Landing page | https://htmldrop.link/ |
| MCP (Streamable HTTP) | POST https://htmldrop.link/mcp |
| REST API | POST https://htmldrop.link/publish |
| This file | https://htmldrop.link/agents.md |
Connect as an MCP client
The server speaks MCP over Streamable HTTP (stateless) — POST each JSON-RPC
message to /mcp. No session handshake or sessionId is required. The response
is returned as application/json, or as a text/event-stream message event
if you send Accept: text/event-stream.
POST https://htmldrop.link/mcp
Content-Type: application/json
Accept: application/json, text/event-stream
{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"agent","version":"1.0"}}}
Then send tools/list and tools/call the same way. Most MCP clients handle
this automatically — see the README for one-line setup (Claude Code, Cursor, …).
Available tool
publish_html
Publish HTML or Markdown and get a public link. Markdown is rendered into a clean reader page server-side.
Schema
{
"name": "publish_html",
"description": "Publish an HTML or markdown artifact to a public URL",
"inputSchema": {
"type": "object",
"properties": {
"html": { "type": "string", "description": "HTML content to publish" },
"markdown": { "type": "string", "description": "Markdown content to publish; rendered to a reader page" },
"title": { "type": "string", "description": "Title used for social cards and metadata" },
"ttl_days": { "type": "number", "description": "Days until the artifact expires" },
"password": { "type": "string", "description": "Optional password to protect the artifact" },
"owner_key": { "type": "string", "description": "Optional owner key for higher rate limits and longer TTL" }
},
"required": ["html"]
}
}
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 · 134 lines · 1,107 tokens per session scan A 9b5244d0fb01
htmldrop AGENTS.md is an instructions file published in the GitHub repository vin-spiegel/htmldrop (13 stars, last pushed 1mo ago), licensed MIT. It adds 1,107 tokens to every session, about $0.0055 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 2026-08-30.
Other instructions, from other repositories
lightpaper CLAUDE.md
Claude Code instructions for lightpaperorg/lightpaper, covering lightpaper.org — claude code instructions, architecture, key files, running locally and running tests.
lightpaper AGENTS.md
AGENTS.md instructions for lightpaperorg/lightpaper, covering agents.md — lightpaper.org, what is lightpaper.org?, quick start, mcp server (recommended for agents) and direct api.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).