draft

A page-creation command for tinydot, a service that turns Markdown files into websites. It creates a new page with the site's metadata, links to related pages, and any needed file references.

In plain words
What is it for?
Use it to draft a page in a chosen tinydot site and folder, add a title, date, tags, Markdown content, and links to existing pages, then save it with a web-friendly filename.
Why use it?
It removes the repetitive work of checking site structure, choosing page metadata, finding related content, and naming the new file correctly.

Command

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.

agentmods
npx agentmods add commands/systemoperators/claude-plugins/draft
Clone the repo
git clone --depth 1 https://github.com/systemoperators/claude-plugins
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 286 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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.

ModelPer sessionOnce invoked
Fable 5 $0.00012 $0.00286
Opus 5 $0.00006 $0.00143
Sonnet 5 $0.00002 $0.00057
Haiku 4.5 $0.00001 $0.00029

Measured yesterday against content hash 7bf044490b63, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

draft 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 yesterday.

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.

tinydot/commands/draft.md · 25 lines

What it actually says

draft a new tinydot page

Create a new markdown page in a tinydot site. Follow these steps:

  1. if no site folder is specified, list available sites in ~/Library/CloudStorage/Tinydot/ and ask which one to use
  2. ask for the topic or title (use $ARGUMENTS if provided)
  3. ask where in the site to create the file (root, or a subfolder)
  4. scan existing pages in the site using Glob for **/*.md to find related content for wikilinks
  5. generate the markdown page with:
    • frontmatter: title, date (today YYYY-MM-DD), tags (relevant tags)
    • well-structured content using standard markdown
    • wikilinks [[page-name]] to link to existing related pages where relevant
    • content blocks for any images or files if applicable
  6. save the file with a kebab-case filename: my-page-title.md
  7. confirm the page is live and show its URL: sitename.tinydot.com/path/to/page

Use the tinydot-content skill for markdown syntax reference.

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.

  1. yesterday First seen · 25 lines · 12 tokens per session scan A 7bf044490b63

Subscribe to this mod's changes

draft is a command published in the GitHub repository systemoperators/claude-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 12 tokens to every session and 286 once invoked, about $0.0001 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.