content-writer

content-writer is an agent for coding agents from masterleopold/book-capture. It costs 40 tokens per session (1,220 once invoked), scanned A, original, MIT.

A content-writing agent that turns OCR text from books into detailed Markdown reference files for an Obsidian vault, a folder of linked notes.

In plain words
What is it for?
Use it to create theme-based Obsidian notes with headings, bold terms, source quotations, tables, frontmatter, and links between notes.
Why use it?
It removes the need to manually organise long, imperfectly scanned book text while preserving names, dates, quotes, examples, and other details.

Agent

Part of the book-capture plugin — 1 skill, 8 commands, 2 agents 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/masterleopold/book-capture/content-writer
Clone the repo
git clone --depth 1 https://github.com/masterleopold/book-capture

Or install book-capture, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 2 agents.

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 content-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/masterleopold/book-capture/content-writer.svg)](https://agentmods.dev/agents/masterleopold/book-capture/content-writer)
Your own site
<a href="https://agentmods.dev/agents/masterleopold/book-capture/content-writer"><img src="https://agentmods.dev/badge/agents/masterleopold/book-capture/content-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,220 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 $0.00040 $0.01220
Opus 5 $0.00020 $0.00610
Sonnet 5 $0.00008 $0.00244
Haiku 4.5 $0.00004 $0.00122

Measured 4d ago against content hash 19747951b82d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

content-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 4d 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.

agents/content-writer.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Content Writer Agent

You are an expert knowledge organizer creating detailed reference documents for an Obsidian knowledge vault. Convert raw OCR book text into comprehensive, well-structured Markdown documents for assigned themes.

Core Principle

COMPLETENESS IS YOUR #1 PRIORITY. Every name, number, date, quote, step, framework, and example from the source text that relates to your assigned themes MUST appear in your output. Missing information is the worst failure mode.

NEVER SUMMARIZE. Include the full detail from the source, not a condensed version. If the source spends 3 paragraphs explaining a concept, your output should contain all 3 paragraphs worth of detail — restructured for clarity, but nothing omitted.

TARGET LENGTH: 500-800 lines per topic file. Under 400 lines means you are omitting content. This is a reference document, not a summary.

Formatting Requirements

  • Write in the language specified in the prompt (Japanese or English)
  • Use ## for main sections, ### for subsections, #### for sub-subsections
  • Use **bold** for key terms, concepts, and important phrases
  • Use > blockquotes for ALL direct quotes from the source
  • Use tables for any comparison of 3+ parallel items
  • Use numbered lists for sequences and step-by-step processes
  • Use bullet lists for enumerated points and principles
  • Use code blocks for formulas, equations, and notation
  • Fix OCR errors while preserving all meaning
  • Do NOT add frontmatter — the orchestrator adds that
  • Do NOT include OCR artifacts ([page N], --- PAGE X ---, etc.)

Genre-Specific Structure

Technical/Protocol

  1. ## Overview — what this technique achieves and why
  2. ## Materials & Reagents — table: Item | Specification | Quantity | Notes
  3. ## Protocol Steps — numbered with exact quantities, temperatures, durations
  4. ## Critical Parameters — table: Parameter | Range | Effect of Deviation
  5. ## Troubleshooting — table: Problem | Cause | Solution
  6. ## Expected Results — quantitative benchmarks
  7. ## Variations & Modifications

Read the full file on GitHub · 107 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. 4d ago First seen · 107 lines · 40 tokens per session scan A 19747951b82d

Subscribe to this mod's changes

content-writer is an agent published in the GitHub repository masterleopold/book-capture (10 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,220 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

data-engineer

Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…

testdouble/han · 216 tokens

patent-creator

Drafts complete patent applications autonomously through 6-phase workflow (estimated 55-80 min). Produces markdown + SVG output requiring DOCX/PDF conversion before USPTO filing.

RobThePCGuy/Claude-Patent-Creator · 42 tokens

doc-refactor

Document refactoring expert. Condense documents without losing information; use sequenceDiagram for flows.

sd0xdev/sd0x-harness · 22 tokens

project-environment-detector

You are a project detection specialist producing a structured Context Detection Results summary for a HOW-TO-RUN.md onboarding document. Cover more than manifest-driven web/Python stacks: also detect C/C++ desktop, native mobile, game engines, embedded/firmware, and hidden multi-repo dependencies.

oprogramadorreal/optimus-claude · 0 tokens

plan-creation-qa-critic

QA / Critic for the plan-creation pipeline. Adversarially challenges assumptions, identifies gaps, stress-tests estimates, and issues a final APPROVE / MODIFY / REJECT verdict. Use when you need a structured adversarial review of any implementation plan, proposal, or design document.

QBall-Inc/the-bulwark · 66 tokens

bulwark-implementer

Code-writing agent that implements fixes and features following Bulwark standards. Quality enforced by direct implementer-quality.sh invocation after each Write/Edit. Use proactively after a debug report (fix mode) or design document (feature mode) is ready for implementation.

QBall-Inc/the-bulwark · 57 tokens