deploy-doc

A command for creating or reorganizing a client-facing deployment or procedure document in Markdown.

In plain words
What is it for?
It helps write a new procedure document or rewrite an existing one, with an optional title, language, and links to separate reference documents.
Why use it?
It removes the need to repeatedly decide how to structure summaries, prerequisites, and ordered instructions.

Command

Part of the docs-forge plugin — 11 skills, 3 commands shipped together

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/youngjaedev/my-claude-plugins/deploy-doc
Clone the repo
git clone --depth 1 https://github.com/YoungjaeDev/my-claude-plugins

Or install docs-forge, the plugin that ships this one along with the rest of its 11 skills, 3 commands.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 715 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 $0.00026 $0.00715
Opus 5 $0.00013 $0.00358
Sonnet 5 $0.00005 $0.00143
Haiku 4.5 $0.00003 $0.00072

Measured 2d ago against content hash a55492edcf3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deploy-doc 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.

plugins/docs-forge/commands/deploy-doc.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploy Doc Command

Produce a consistent client-facing deployment / procedure document (.md): a top-of-file summary, a prerequisites checklist, and numbered procedure steps. The enforceable skeleton lives in the deploy-doc-guide skill (the cross-runtime SSOT); this command orchestrates Read/Write around it.

Arguments

  • generate - Author a new procedure doc from collected input.
  • rewrite - Restructure an existing .md into the skeleton, preserving its content.

Options

  • --title TITLE - Document title, emitted as the # H1 on the first line (above the untitled summary paragraph). If omitted, ask or infer from input.
  • --lang ko|en - Output language. Default ko.
  • --links <doc1,doc2> - SSOT documents the procedure links to instead of redefining (detailed contracts / specs that must NOT be inlined).

Instructions

For generate

  1. Load the deploy-doc-guide Skill — its ## Quick Reference is the binding skeleton + self-verify checklist.
  2. Collect: title, a 2-3 line core summary, prerequisite items, and the ordered procedure steps.
  3. Emit the skeleton in this order:
    • # H1 document title from --title (first line). Omit only when no title is given/inferable.
    • Untitled summary paragraph (2-3 lines, no section heading) directly below the title and above the first ##.
    • ## 전제조건 (or ## Prerequisites for --lang en) — every item as a - [ ] checklist line.
    • ## 절차 (or ## Procedure) — each step as ### 1. / ### 2. / ### N., contiguous numbering from 1.
  4. Number-match rule: the count of steps named/implied in the summary MUST equal the number of ### N. headings.
  5. Link, don't redefine: detailed contracts and SSOT details go to the --links documents as links; never inline them.

For rewrite

  1. Read the target file.
  2. Map existing content onto the skeleton:
    • Move redefined contracts/specs to links (demote inline contracts to --links references).
    • Renumber procedure prose into contiguous ### N. headings.
    • Lift or synthesize the 2-3 line summary to the top as an untitled paragraph.
  3. Preserve original prose verbatim where possible — this is a surgical restructure, not a rewrite of wording.

Read the full file on GitHub · 65 lines

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. 2d ago First seen · 65 lines · 26 tokens per session scan A a55492edcf3b

Subscribe to this mod's changes

deploy-doc is a command published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed 7d ago), licensed MIT. It adds 26 tokens to every session and 715 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.