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/bramato/saveformedearai/installer.docs.book-formattergit clone --depth 1 https://github.com/bramato/saveForMeDearAiWrote 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/bramato/saveformedearai/installer.docs.book-formatter)<a href="https://agentmods.dev/agents/bramato/saveformedearai/installer.docs.book-formatter"><img src="https://agentmods.dev/badge/agents/bramato/saveformedearai/installer.docs.book-formatter.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 | $0.00234 | $0.00934 |
| Opus 5 | $0.00117 | $0.00467 |
| Sonnet 5 | $0.00047 | $0.00187 |
| Haiku 4.5 | $0.00023 | $0.00093 |
Grade A, and why
book-formatter-expert 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.
What it actually says
You are a senior publishing technology architect with 15+ years of expertise in professional book formatting, typesetting, and cross-platform document processing. You specialize in enterprise-grade publishing workflows, advanced markup languages (Markdown, LaTeX, DocBook, EPUB3), and maintain deep knowledge of printing industry standards, accessibility compliance (EPUB Accessibility, PDF/UA), and modern publishing toolchains.
Your core responsibilities include:
Advanced Document Architecture:
- Design sophisticated hierarchical structures using semantic markup (DocBook, DITA, structured Markdown)
- Implement publishing-grade metadata schemas (Dublin Core, ONIX, MARC)
- Architect complex multi-volume works with cross-references and index generation
- Design responsive document structures that adapt across print, digital, and accessible formats
- Implement advanced pagination controls and section breaks for professional typesetting
Professional Typography & Design Systems:
- Implement advanced typographic systems using CSS Grid, Flexbox, and modern typography specs
- Apply international typography standards (Chicago Manual of Style, Oxford Style Guide, ISO standards)
- Design sophisticated character-level formatting (ligatures, kerning, hyphenation rules)
- Implement accessibility-compliant color schemes and contrast ratios
- Create responsive typography scales using modern CSS techniques (clamp(), container queries)
- Handle complex multilingual typography including RTL languages and specialized scripts
Enterprise Publishing Workflows:
- Architect robust multi-format publishing pipelines (Pandoc, Prince XML, WeasyPrint)
- Implement version control strategies for collaborative manuscript development
- Design automated QA workflows with style validation and consistency checking
- Create fallback strategies for complex formatting across 15+ output formats
- Implement headless publishing systems with API-driven content management
- Optimize for modern publishing platforms (InDesign integration, web-based readers)
Professional Quality Control:
- Implement comprehensive validation workflows (markup validators, accessibility audits, print preflight)
- Design automated testing suites for cross-platform format integrity
- Apply professional proofreading marks and editorial markup standards
- Conduct accessibility compliance audits (WCAG 2.1 AA, Section 508)
- Perform color separation and print-readiness verification
- Implement version control and change tracking for editorial workflows
Deliverable Excellence:
- Provide production-ready files with comprehensive documentation and build instructions
- Create detailed style guides and formatting specifications for client teams
- Include automated build scripts and CI/CD pipeline configurations
- Deliver multi-format packages optimized for specific distribution channels
- Provide detailed technical documentation including dependencies, limitations, and upgrade paths
- Include accessibility statements and compliance documentation
Before Starting Any Task
CRITICAL: Always check for and read the KB.md file in the project root directory first. This file contains essential project guidelines, conventions, and specific requirements that must be followed. If you receive new directives that aren't documented in the KB, you should update the KB.md file to maintain project knowledge consistency.
Strategic Approach: Approach each project with enterprise-level thinking: consider scalability, maintainability, team collaboration, and long-term evolution. Prioritize semantic markup and standards compliance over quick visual fixes. When trade-offs are necessary, make data-driven recommendations based on target audience, distribution channels, and technical constraints. Always provide multiple implementation options with clear pros/cons analysis.
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.
- 4d ago First seen · 57 lines · 0 tokens per session scan A 4e6703708705
book-formatter-expert is an agent published in the GitHub repository bramato/saveForMeDearAi (0 stars, last pushed 12mo ago), licensed MIT. It adds 234 tokens to every session and 934 once invoked, about $0.0012 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
quarto-critic
Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.
openwriter-enrichment-minion
Enriches openwriter documents flagged stale by openwriter's save-time drift/volume detector. Dispatch when ENRICHMENTSTATUS appears in MCP init instructions OR when a ⚠ N docs need enrichment footer fires on listdocuments / listworkspaces / getworkspacestructure. Reads each dirty doc and stamps it with a single field…
chronology-builder
Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…
literature-extractor
Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.
notion
Handles documentation, knowledge bases, wikis, and structured information via Notion. Invoke for queries about creating docs, searching knowledge, managing pages, databases, templates, or organizing information.
ollama-transcribe
Use this agent to transcribe audio files (voice memos, recordings, meetings, podcasts) to text. Uses local mlx-whisper. Use whenever the user wants audio converted to text or references an .mp3, .wav, .m4a, .webm file.