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.
npx agentmods add agents/queelius/claude-anvil/section-writergit clone --depth 1 https://github.com/queelius/claude-anvilWrote 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.
[](https://agentmods.dev/agents/queelius/claude-anvil/section-writer)<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>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.
| Model | Per session | Once 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 |
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.
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:
- The plan task spec for this section (content checklist, page budget, label requirements, notation requirements). The plan lives under
docs/superpowers/plans/. book/CLAUDE.mdfor repo layout, the build command, macro package name, and style rules.docs/superpowers/bookwright.config.yamlfor any project-level overrides.- The two or three sections immediately preceding this one, for voice and notation continuity.
- 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.mdfor 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.
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.
- 3d ago First seen · 88 lines · 45 tokens per session scan A 3675e181e5da
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.
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.
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.
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…
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.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.
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.