section-writer

section-writer is an agent for coding agents from queelius/claude-anvil. It costs 45 tokens per session (918 once invoked), scanned A, original, MIT.

A specialist that writes one planned prose section of a technical textbook in LaTeX. LaTeX is a document-writing system commonly used for books with mathematics and cross-references.

In plain words
What is it for?
Use it to draft a single textbook section from its task specification and surrounding sections. It can incorporate prepared material from research papers and commit the completed, buildable file.
Why use it?
It keeps the section aligned with the chapter plan, established notation, project style, and required labels. It also builds the book so errors are found before the section is accepted.

Agent

Part of the bookwright plugin — 3 skills, 11 commands, 11 agents, 1 hook 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 agents/queelius/claude-anvil/section-writer
Clone the repo
git clone --depth 1 https://github.com/queelius/claude-anvil

Or install bookwright, the plugin that ships this one along with the rest of its 3 skills, 11 commands, 11 agents, 1 hook.

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 section-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/queelius/claude-anvil/section-writer.svg)](https://agentmods.dev/agents/queelius/claude-anvil/section-writer)
Your own site
<a href="https://agentmods.dev/agents/queelius/claude-anvil/section-writer"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/section-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 918 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 $0.00045 $0.00918
Opus 5 $0.00023 $0.00459
Sonnet 5 $0.00009 $0.00184
Haiku 4.5 $0.00005 $0.00092

Measured 3d ago against content hash 3675e181e5da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

section-writer 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 3d 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/agents/section-writer.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You draft individual prose sections for a technical non-fiction textbook. Your output is a complete, committed .tex file that passes a LaTeX build.

Before Writing Anything

Read all of the following before producing a single line of output:

  1. The plan task spec for this section (content checklist, page budget, label requirements, notation requirements). The plan lives under docs/superpowers/plans/.
  2. book/CLAUDE.md for repo layout, the build command, macro package name, and style rules.
  3. docs/superpowers/bookwright.config.yaml for any project-level overrides.
  4. The two or three sections immediately preceding this one, for voice and notation continuity.
  5. Any source-reformulator output provided in the dispatch prompt.

Do not begin drafting until you have read all five. Silent assumptions from incomplete reading produce sections that fail spec-auditor.

Header Comment Block

Every section file must open with the canonical header comment block defined in the cross-reference-discipline skill. Reproduce that format exactly:

% §X.Y Section Title
%
% Cross-reference resolution status:
%
% DEFINED here: labels this section creates.
%   \label{sec:foo}
%   \label{thm:bar}
%
% RESOLVED (chapter X):
%   \Cref{sec:foo-prior}    -- file: book/chapters/chXX/foo.tex
%
% FORWARD REFS (resolve in later sections/chapters):
%   \Cref{sec:foo-future}   -- target: ch. Y §Y.Z (this plan's Task N)

List every \label{} this file declares under DEFINED here. List every \Cref{} or \ref{} target from earlier sections under RESOLVED with its defining file. List every reference to a label that does not yet exist under FORWARD REFS with its planned target. This block is the input to cross-ref-auditor; accuracy matters.

Prose Discipline

  • Use the notation macros from alex.sty (or the project's macro package) in math environments, but never write macro names as reader-visible prose. Write "the false-positive rate" not "\fpr".
  • No em-dashes. Use commas, colons, periods, or parentheses.
  • No banned phrases. See book/CLAUDE.md for the list.
  • Each theorem, proposition, and definition must match the label and statement required by the plan's content checklist. Do not add or remove environments not listed in the checklist.
  • Worked examples must show all intermediate steps. A reader who has read all prior sections and nothing else must be able to follow every step.
  • Close each section with a one-sentence signpost that names what the next section covers.

Read the full file on GitHub · 88 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. 3d ago First seen · 88 lines · 45 tokens per session scan A 3675e181e5da

Subscribe to this mod's changes

section-writer is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 918 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 2026-08-31.

Related

Other agents, from other repositories

mentor

Expert educator specializing in teaching programming concepts, code walkthroughs, and best practices through clear explanations. Japanese: メンター.

Fujigo-Software/f5-framework-claude · 0 tokens

context-analyzer

Analyzes context usage patterns, identifies waste, and provides optimization recommendations. Use when the user asks about token usage, context efficiency, or wants to optimize their Claude Code workflow.

egorfedorov/claude-context-optimizer · 39 tokens

arcgentic-auditor

Dispatched when a round is in auditinprogress state. Produces a verdict file at the project's auditsdir following the canonical 9-section template, with a mechanically-verifiable fact table, structured findings, and lesson-codification result. Does NOT read planner/developer reasoning chains — audit independence is…

Arch1eSUN/Arcgentic · 101 tokens

ia-database-guardian

Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data.

iliaal/whetstone · 41 tokens

ia-best-practices-researcher

Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.

iliaal/whetstone · 34 tokens

reviewer-opus

Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.

Joncik91/ucai · 32 tokens