docs.init

A command that creates the initial documentation structure for a project using Diátaxis, a way to separate tutorials, how-to guides, explanations, and reference material. It also creates files that record documentation plans, terminology, sources, and progress.

In plain words
What is it for?
Use it to establish a docs/ directory, add user and developer documentation areas, create documentation tracking files, and identify the next documentation task.
Why use it?
It gives a project a consistent documentation layout and records what has been documented. It checks the existing project before creating or updating files.

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/ddunnock/claude-plugins/docs.init
Clone the repo
git clone --depth 1 https://github.com/ddunnock/claude-plugins
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 264 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 $0.00000 $0.00264
Opus 5 $0.00000 $0.00132
Sonnet 5 $0.00000 $0.00053
Haiku 4.5 $0.00000 $0.00026

Measured 2d ago against content hash 09668dc88a99, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs.init 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.

skills/documentation-architect/commands/docs.init.md · 43 lines

What it actually says

Establish documentation foundation for this project.

Before Starting

Read and internalize the behavioral constraints in GUARDRAILS.md.

Workflow

  1. Check existing state (docs/, .claude/memory/docs-*.md)
  2. Detect project type (library, CLI, app, service)
  3. Create docs/ structure with Diátaxis layout
  4. Create documentation memory files
  5. Present summary and next steps

Outputs to Create

docs/
├── index.md
├── user/
│   ├── getting-started/
│   ├── guides/
│   ├── concepts/
│   └── reference/
├── developer/
│   ├── architecture/
│   ├── contributing/
│   └── reference/api/
└── _meta/
    ├── inventory.md
    ├── plan.md
    └── progress.md

.claude/memory/
├── docs-constitution.md
├── docs-terminology.md
└── docs-sources.md

Guardrails

  • No assumptions without approval
  • No proceeding without confirmation
  • Idempotent: skips existing, updates changed, preserves customizations

After completion, suggest /docs.inventory as next step.

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 · 43 lines · 0 tokens per session scan A 09668dc88a99

Subscribe to this mod's changes

docs.init is a command published in the GitHub repository ddunnock/claude-plugins (12 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 264 tokens. 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 2026-08-30.