docs-write

docs-write is a command for Claude Code from axiomantic/spellbook. It costs 31 tokens per session (4,151 once invoked), scanned A, original, MIT.

A documentation-generation step that creates project documentation from an approved plan, using different writing styles for different sections and Diátaxis, a framework that separates tutorials, how-to guides, explanations, and references.

In plain words
What is it for?
Generating documentation files from project code and an approved documentation plan.
Why use it?
It keeps documentation aligned with the planned structure and intended purpose of each section.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions subagents; names the AskUserQuestion tool.

Good fit Generating documentation files from project code and an approved documentation plan.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/axiomantic/spellbook/docs-write
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.

Clone the repo
git clone --depth 1 https://github.com/axiomantic/spellbook

Made for: Claude Code.

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.

agentmods badge for docs-write

README.md
[![agentmods](https://agentmods.dev/badge/commands/axiomantic/spellbook/docs-write/github.svg)](https://agentmods.dev/commands/axiomantic/spellbook/docs-write)
Your own site
<a href="https://agentmods.dev/commands/axiomantic/spellbook/docs-write"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/docs-write/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.

agentmods 80×15 button for docs-write

Your own site · 80×15
<a href="https://agentmods.dev/commands/axiomantic/spellbook/docs-write"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/docs-write.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,151 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 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 5.1 $0.00031 $0.04151
Opus 5 $0.00015 $0.02076
Sonnet 5 $0.00006 $0.00830
Haiku 4.5 $0.00003 $0.00415

Measured 5d ago against content hash a7e1561971f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

docs-write 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 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.

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.

commands/docs-write.md · 389 lines

How it starts

The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MISSION

Generate documentation files according to the approved plan, enforcing Diataxis structure and tone profiles per section. Write files directly to the project repository. For each section, assemble source code context, load the matching tone profile and template skeleton, apply writing guide rules during generation, and dispatch a writing subagent. Record all generation results for the review phase. Support selective regeneration via sections_filter for iteration loops.

Invariant Principles

  1. Tone profile adherence: Each section follows its assigned tone profile from the plan. Drift between profiles within a document is a defect.
  2. Diataxis skeleton compliance: Each section follows the structural skeleton from doc-templates.md for its declared Diataxis type. Structural deviations cause review failures.
  3. Writing guide rules applied during generation: The writing subagent receives the full writing guide rules as part of its prompt. These rules are generative constraints, not post-hoc filters.
  4. Output to project repository: Documentation files are project deliverables. Write to the output_path specified in the plan, relative to the project root. Never write docs to spellbook artifact directories.
  5. Selective regeneration merges: When sections-filter.json is present, only regenerate listed sections. Merge new results into the existing written-manifest.json rather than replacing it.

Read the full file on GitHub · 389 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. 5d ago First seen · 389 lines · 31 tokens per session scan A a7e1561971f4

Subscribe to this mod's changes

docs-write is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 4,151 once invoked, about $0.0002 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 2026-09-03.

Related

Other commands, from other repositories