draft

A command that starts the bookwright writing process for a whole chapter or one textbook section. It coordinates drafting specialists and then runs checks on the resulting material.

In plain words
What is it for?
Use it to draft a complete chapter or a specific section from the book plan. Depending on the task, it can involve prose writers, notebook authors, source reformulators, specification checks, and quality checks.
Why use it?
It removes the need to manually start each writing and review step. When reviewers find substantive problems, it sends the work back for correction and verification.

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/queelius/claude-anvil/draft
Clone the repo
git clone --depth 1 https://github.com/queelius/claude-anvil
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 351 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 $0.00015 $0.00351
Opus 5 $0.00008 $0.00176
Sonnet 5 $0.00003 $0.00070
Haiku 4.5 $0.00002 $0.00035

Measured 2d ago against content hash 4a95281c8c65, 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 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.

bookwright/commands/draft.md · 30 lines

What it actually says

/bookwright:draft

Launch the writer orchestrator agent to draft prose. Argument can be a whole chapter (the writer iterates through its per-section tasks) or a single section path (one task end-to-end).

What the writer does (briefly)

For each section task in the relevant plan:

  1. Reads the plan's content checklist and content-source list.
  2. Dispatches the appropriate drafting specialist:
    • section-writer for narrative prose.
    • notebook-author if the task includes a paired notebook.
    • source-reformulator if the task requires reformulating an external paper.
  3. After the draft commits, dispatches spec-auditor and quality-auditor in parallel for review.
  4. If either auditor surfaces substantive findings, re-dispatches section-writer with the finding as input and re-runs the relevant auditor to verify the fix.
  5. Reports the task's commit SHAs and word counts back to the user.

When to use what

  • /bookwright:draft chapter5 runs ALL section tasks of chapter 5 in sequence (scaffold first, then sections, then bib + exercises, then notebook).
  • /bookwright:draft ch05/bloom-from-scratch.tex runs only that one section task.

For per-Part or full-book integration verification, use /bookwright:integrate instead. For editorial review of an existing chapter (no drafting), use /bookwright:review.

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 · 30 lines · 15 tokens per session scan A 4a95281c8c65

Subscribe to this mod's changes

draft is a command published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 351 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.