claude

bookwright

Documentation-first methodology and multi-agent toolchain for technical non-fiction long-form manuscripts. The Bernoulli-textbook approach: design spec and chapter plans drive the manuscript.

2 on GitHubby Alexander Towellv0.4.0MITupdated 10 days agowriting
/

Plugin bookwright from marketplace queelius-plugins in queelius/claude-anvil. Commands read from the repo's manifest — 10 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (3)

  • cross-reference-discipline

    Use when writing cross-referenced sections in a bookwright project. Covers the header comment block template, label-naming conventions, when to use prose-only vs Cref, forward-reference documentation, and the integration-check baseline.

  • notebook-paired-with-prose

    Use when drafting or executing a paired notebook for a bookwright chapter. Covers when notebooks are required vs optional, numerical-sanity-target convention, exec-from-fresh-kernel requirement, and stack-specific execution commands (Jupyter/R Markdown/Quarto).

  • textbook-methodology

    Use when drafting prose sections for a bookwright (technical non-fiction) project. Covers atom-outward design, deferral discipline, running threads, page budgets, per-section subagent cadence, and commit discipline.

Slash commands (11)

  • /bookwright:check

    Fast mechanical diagnostics on a section, chapter, part, or full book

  • /bookwright:design

    Write a master spec or per-Part design spec via Socratic dialogue with the user

  • /bookwright:draft

    Launch the writer orchestrator for prose drafting (whole chapter or single section)

  • /bookwright:help

    Quick reference for bookwright commands, agents, and skills

  • /bookwright:init

    Scaffold a fresh non-fiction book project (LaTeX + pluggable notebook + spec/plan directories)

  • /bookwright:integrate

    Per-Part or full-book integration check with a written integration-pass record

  • /bookwright:iterate

    Autonomous review-fix-review loop until convergence, plateau, or the iteration cap

  • /bookwright:notebook

    Draft and execute the paired notebook for a chapter (separable from prose drafting)

  • /bookwright:plan

    Write a per-chapter implementation plan from the relevant design spec

  • /bookwright:review

    Heavy multi-agent editorial review (4 specialist auditors in parallel)

  • /bookwright:revise

    Apply fixes from a review report via the rewriter orchestrator (fix-then-verify)

Subagents (11)

  • cross-ref-auditor

    Verifies cross-reference integrity: Cref targets, label collisions, and undefined-reference categorization. Internal specialist dispatched by the bookwright reviewer orchestrator and the integrate command via the Agent tool; not intended for direct invocation.

  • iterator

    Autonomous review-fix-review loop orchestrator for technical non-fiction textbooks (bookwright). Alternates the reviewer and rewriter until convergence, plateau, or the iteration cap, with delta-scoped rounds and a single end-of-loop checkpoint for high-stake judgment calls. <example> Context: User

  • math-auditor

    Recomputes arithmetic, derivations, and worked examples independently via Python. Internal specialist dispatched by the bookwright reviewer orchestrator via the Agent tool; not intended for direct invocation.

  • notebook-author

    Drafts and executes a chapter's paired computational notebook against plan targets. Internal specialist dispatched by the bookwright writer orchestrator and the `/bookwright:notebook` command via the Agent tool; not intended for direct invocation.

  • quality-auditor

    Cold-reads a drafted section for pedagogical clarity and prose craft without consulting the plan. Internal specialist dispatched by the bookwright writer and reviewer orchestrators via the Agent tool; not intended for direct invocation.

  • reviewer

    Multi-agent editorial review orchestrator for technical non-fiction textbooks (bookwright). Runs the spec, quality, math, and cross-ref auditors in parallel over a section, chapter, part, or the book and saves one unified findings report. Does not fix anything. <example> Context: User wants a full c

  • rewriter

    Multi-agent revision orchestrator for technical non-fiction textbooks (bookwright). Applies a review report's findings with fix-then-verify: drafting specialists or direct edits fix, the originating auditor verifies, and a paired revision report records the result. <example> Context: User has a revi

  • section-writer

    Drafts a single textbook prose section per the chapter plan spec, builds the book, and commits on success. Internal specialist dispatched by the bookwright writer orchestrator via the Agent tool; not intended for direct invocation.

  • source-reformulator

    Reformulates source-paper content into fresh pedagogical prose as input for section drafting. Internal specialist dispatched by the bookwright writer orchestrator via the Agent tool; not intended for direct invocation.

  • spec-auditor

    Verifies a drafted section against the chapter plan checklist, page budget, and label requirements. Internal specialist dispatched by the bookwright writer and reviewer orchestrators via the Agent tool; not intended for direct invocation.

  • writer

    Multi-agent drafting orchestrator for technical non-fiction textbooks (bookwright). Drafts a chapter or section from its plan: dispatches drafting specialists per section, audits each draft (spec and quality in parallel), and loops on fixes. Drafts from plans only; review-driven fixes belong to the

Hooks (1)

  • PostToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/check_latex_macro_leak.py"

View source on GitHub

More from queelius/claude-anvil

All 12 plugins →

papermill

claude

Research paper lifecycle management: thesis refinement, literature surveys, experimental design, multi-agent drafting, editorial review, and publication venue matching

13 skills · 16 agents

2

Documentation-first worldbuilding methodology and prose craft guardrails for fiction projects. The Silmarillion approach: docs ARE the world, story text derives from them.

2 skills · 8 commands · 11 agents · hooks

2

Unified publication pipeline: R packages (CRAN/JOSS/JSS) and Python packages (PyPI)

5 skills · 5 agents

2

repoindex

claude

Repository intelligence for Claude Code. MCP-first access to a local git catalog, two agents (repo-polish, repo-explorer), and five slash commands (/repo-week, /repo-status, /repo-audit, /repo-sprint, /repo-mirror) for recurring workflows.

1 skill · 5 commands · 2 agents

2

crier

claudecodex

Cross-post blog content to multiple platforms: audit, publish, rewrite, and track content distribution via the crier CLI

1 skill · 1 command · 2 agents · 1 MCP server · hooks

2

Autonomous research agent: iterates toward a goal through proofs, code, simulations, tests, and counterexample search

5 skills · 1 agent

2

Similar plugins

agentdb

claude

AgentDB (external: maintained in ruvnet/agentdb, pinned to commit 27678c3, plugin 3.6.0): agentdb's own standalone MCP server pinned to [email protected] (vector memory with get/list/update/delete for records, patterns and skills, hybrid keyword + vector episode search and an opt-in local cross-encoder, an opt-in aidefence injection guard on memory writes, reflexion, skills, outcome feedback, capabilities report), a memory-specialist agent, 3 skills, /agentdb-status, and the agentdb mod guard that keeps secrets out of memory and refuses delete/reset unless allowed. Complements ruflo-agentdb, which reaches AgentDB through ruflo's server

3 skills · 1 command · 1 agent · 1 MCP server

ruvnet/ruflo 81,589

humanizer

claude

Rewrite AI-sounding text so it reads like the writer without changing what it says.

1 skill

blader/humanizer 68,461

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

Connect Claude Code directly to your CockroachDB clusters for hands-on database work — explore schemas, write optimized SQL, debug queries, and manage distributed database clusters. This plugin provides 14 tools across two active MCP backends (self-hosted MCP Toolbox and managed CockroachDB Cloud MCP Server), three specialized agents (DBA, Developer, Operator), 32 skills across 6 operational domains, and built-in safety hooks.

34 skills · 3 agents · 3 MCP servers · hooks

anthropics/claude-plugins-official 47,076

OpenAPI specification generation, Mermaid diagram creation, tutorial writing, API reference documentation

3 skills · 1 command · 5 agents

wshobson/agents 42,461

Provision direct cloud access (Vertex AI, Bedrock, or LLM gateway) for the Claude Microsoft 365 add-in. Generates the customized manifest, walks through Azure admin consent, and writes per-user config via Graph extension attributes.

1 skill · 9 commands

anthropics/financial-services 41,259

Maintain bookwright?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins12 plugins