A tool for publishing an HTML, Markdown, PDF, file, or complete website as a private link on your own domain, optionally protected by a password.

Use it to publish or share reports, pages, documents, and other generated files through branded links with optional client-side encryption.

It removes the need to deploy each shared artifact separately and can keep shared content out of search indexes.

hushdrop — Skill for Claude Code by maxtechera

Install

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.

Any agent

npx skills add maxtechera/hushdrop --skill skill

Clone the repo

git clone --depth 1 https://github.com/maxtechera/hushdrop

Made for: Claude Code.

Or install hushdrop, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/maxtechera/hushdrop/skill/github.svg)](https://agentmods.dev/skills/maxtechera/hushdrop/skill)

Your own site

<a href="https://agentmods.dev/skills/maxtechera/hushdrop/skill"><img src="https://agentmods.dev/badge/skills/maxtechera/hushdrop/skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/maxtechera/hushdrop/skill"><img src="https://agentmods.dev/badge/skills/maxtechera/hushdrop/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,330 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 100% copy Near-identical to another mod in the catalogue.

Token cost

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	$0.00105	$0.01330
Opus 5.5	$0.00042	$0.00532
Sonnet 5.5	$0.00021	$0.00266
Haiku 4.5	$0.00011	$0.00133

Measured 2mo ago against content hash 83794c2a82d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hushdrop 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 2mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (drop.mjs, install.mjs, mcp.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

100% identical to hushdrop — 0 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.

skill/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hushdrop

Open-source artifact sharing on your own domain. Drop a file → it's branded, optionally password-locked (AES-256, client-side), and live at a clean URL in ~1 second. No git, no deploy-per-file — it's object storage (Vercel Blob) behind a one-line edge proxy.

When to use

Reach for drop when the user asks to publish / share / host / send something, or whenever you've generated an HTML page (report, dashboard, mockup, doc) they'll want to view in a browser. Pipe the artifact to drop and hand back the URL (and password, if locked).

Two ways to run

Zero-setup (managed): hush file.html --managed — no token, no Vercel. Publishes to the managed tier (HTML/markdown, auto-expires in 24h). Easiest start.
Your own domain: hush init once (BYO Vercel Blob + domain, see SETUP.md), then hush file.html.

Default posture

Locked by default (AES-256, client-side — the server only stores ciphertext). Every drop is served noindex so leaked URLs never get indexed. Use a long password for anything sensitive.

Usage

hush report.html               # brand + lock (auto password) + upload → https://<domain>/report-a1b2
drop notes.md                  # markdown → rendered, branded HTML page
hush report.html -p secret     # use your own password
hush report.html --no-lock     # branded, no password (renders for anyone with the link)
hush report.html --expire 7d   # auto-expire (7d/24h/2w/date); enforce deletion with `hush gc`
drop bundle.zip                # raw file, unguessable URL → /bundle-x7f2k9.zip
drop file.pdf --page           # generate a branded download page wrapping the file
drop file.pdf --page -p secret # password-protect that download page
drop -s q3-deck deck.html      # force the slug → /q3-deck
hush list                      # list live drops + their passwords
hush rm q3-deck                # delete a drop
hush gc                        # delete drops whose --expire has passed (cron-friendly)

MCP server: node skill/mcp.mjs exposes publish_html, publish_file, update_site, list_sites, delete_site over stdio. Wire it into agents with node skill/install.mjs.

Read the full file on GitHub · 94 lines

Files

What ships with it

14 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.

Changes

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.

2mo ago First seen · 94 lines · 105 tokens per session scan A 83794c2a82d4

Subscribe to this mod's changes

hushdrop is a skill published in the GitHub repository maxtechera/hushdrop (8 stars, last pushed 4mo ago), licensed MIT. It adds 105 tokens to every session and 1,330 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to hushdrop, differing in 0 lines, and is treated as a copy.

Claude Code Documents PDF ai-agents anthropic artifact-sharing claude cli

hushdrop next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
hushdropmaxtechera/hushdrop	Skill	8	4mo ago	MIT	A	105	Claude Code
illustrated-slides-with-nano-bananadeancourse/user-dot-agents	Skill	7	4mo ago	MIT	A	71	Claude Code, Codex
nano-pdfprofclaw/profclaw	Skill	16	1mo ago	AGPL-3.0	A	32	Claude Code, Codex
pdfopencue/cuecards	Skill	7	yesterday	MIT	A	92	Claude Code, Codex
nano-pdfStarryCod/cogitum	Skill	12	5mo ago	MIT	A	21	Claude Code, Codex
ocr-and-documentsStarryCod/cogitum	Skill	12	5mo ago	MIT	A	21	Claude Code, Codex
wowerpointthedotmack/claude-mem	Skill	114k	yesterday	Apache-2.0	A	53	Claude Code