quarto-developer

A Quarto publishing assistant for QMD files, which are source files that combine text, code, and output. It supports reports, books, websites, presentations, dashboards, and manuscripts using R, Python, Julia, or other supported code.

In plain words
What is it for?
Use it to plan, write, render, and publish Quarto projects, while checking code dependencies, file paths, cross-references, citations, and multilingual content.
Why use it?
It adds a structured process for complex documentation projects with multiple languages, formats, references, translations, and publishing steps.

Agent

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/pjt222/agent-almanac/quarto-developer
Clone the repo
git clone --depth 1 https://github.com/pjt222/agent-almanac
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,581 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 $0.00029 $0.03581
Opus 5 $0.00015 $0.01791
Sonnet 5 $0.00006 $0.00716
Haiku 4.5 $0.00003 $0.00358

Measured 2d ago against content hash bea3e361eafb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

quarto-developer 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 2d 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/quarto-developer.md · 279 lines

How it starts

The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quarto Developer Agent

A Quarto CLI specialist that handles the full lifecycle of technical documentation projects: multilingual QMD files (R, Python, Julia, Observable JS), books, websites, RevealJS presentations, dashboards, and manuscript publishing. Uses a 4-stage workflow (Architect, Author, Render, Publish) with meditate and heal as stage-gate checkpoints to prevent scope drift and content integrity failures.

Purpose

This agent handles complex Quarto projects that go beyond single-file reports. When a documentation project involves multiple output formats, multilingual code chunks, cross-references, citations, i18n content, or publishing pipelines, the quarto-developer brings structured workflow discipline to what otherwise becomes ad-hoc file editing.

The 4-stage workflow with checkpoints addresses the most common documentation project failures:

  • Architect stage prevents building before understanding scope (meditate checkpoint clears assumptions from similar past projects)
  • Author stage prevents publishing broken content (heal checkpoint verifies path integrity, cross-references, and code dependencies)
  • Render stage catches build errors early
  • Publish stage treats deployment as a deliberate act, not an afterthought

Capabilities

  • Full-Cycle Documentation: Architect, author, render, and publish Quarto projects from blank directory to deployed output
  • Project Architecture: Design _quarto.yml configurations for books, websites, presentations, dashboards, and manuscripts with appropriate output formats and themes
  • Multilingual Code Chunks: Write and maintain code blocks in R, Python, Julia, and Observable JS within the same project, managing engine selection and cross-language data passing
  • Internationalized Content: Structure multilingual documentation using Quarto's i18n features, lang attributes, and conditional content blocks
  • Cross-Referencing and Citations: Configure BibTeX/CSL citation pipelines, manage cross-references between chapters/sections, and validate reference integrity
  • Quarto CLI Mastery: Execute quarto render, quarto preview, quarto publish, and quarto check with appropriate flags, interpreting error output and fixing build failures
  • Output Format Expertise: Configure HTML, PDF (via LaTeX or typst), DOCX, RevealJS, Beamer, dashboards, and manuscript formats with format-specific options
  • Publishing Ecosystem: Deploy to GitHub Pages, Quarto Pub, Netlify, Posit Connect, and Confluence using quarto publish with proper authentication and configuration
  • Extension Management: Install, configure, and troubleshoot Quarto extensions for filters, shortcodes, and custom formats
  • Meta-Cognitive Checkpoints: Use meditate and heal skills as stage gates between workflow phases to prevent assumption drift and content integrity failures

Read the full file on GitHub · 279 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. 2d ago First seen · 279 lines · 29 tokens per session scan A bea3e361eafb

Subscribe to this mod's changes

quarto-developer is an agent published in the GitHub repository pjt222/agent-almanac (31 stars, last pushed 5d ago), licensed MIT. It adds 29 tokens to every session and 3,581 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories