A workflow guide for editing or reviewing Kitaru documentation, examples, generated reference pages, redirects, and documentation checks. Kitaru documentation includes hand-written Markdown and generated SDK and command-line references.

Use it when changing documentation, examples, navigation, redirects, generated API references, command-line references, or documentation CI behavior.

It explains which files own each type of documentation and how the publishing and generation process works. This helps prevent edits from going into the wrong documentation surface.

How zenml-io/kitaru configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to zenml-io/kitaru. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/zenml-io/kitaru/develop/.agents/skills/kitaru-docs/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/zenml-io/kitaru

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zenml-io/kitaru/kitaru-docs.svg)](https://agentmods.dev/skills/zenml-io/kitaru/kitaru-docs)

Your own site

<a href="https://agentmods.dev/skills/zenml-io/kitaru/kitaru-docs"><img src="https://agentmods.dev/badge/skills/zenml-io/kitaru/kitaru-docs.svg" alt="Measured on agentmods" height="20"></a>

Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 848 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00013	$0.00848
Opus 5	$0.00006	$0.00424
Sonnet 5	$0.00003	$0.00170
Haiku 4.5	$0.00001	$0.00085

Measured 7d ago against content hash 46bec8696a49, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

kitaru-docs 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 7d 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/skills/kitaru-docs/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kitaru Documentation Workflow

Use this when editing or reviewing Kitaru documentation, examples, generated reference docs, docs redirects, or docs CI behavior.

Documentation Surfaces

Kitaru docs live on three surfaces:

Hand-written docs are plain Markdown in docs/book/, published to docs.zenml.io/kitaru through GitBook Git Sync. Navigation is docs/book/toc.md, configuration is docs/book/.gitbook.yaml, and authoring conventions live in docs/book/AGENTS.md.
Generated SDK and CLI reference docs live in the FumaDocs app under docs/, with output under docs/content/docs/reference/ served from sdkdocs.kitaru.ai. scripts/generate_sdk_docs.py extracts the allowlisted Python API, and scripts/generate_cli_docs.py reads the offline kitaru schema contract. Run both through just generate-docs.
kitaru.ai/docs/* redirects are handled by docs/worker/redirect.mjs and wrangler.redirect.toml.

Do not add hand-written pages to docs/content/docs/. The public changelog is owned by the changelog repository at docs.zenml.io/changelog. This repository may generate a gitignored docs/content/docs/changelog.mdx for local reference builds, but agents should not hand-edit or commit it.

The public marketing/runtime site lives in zenml-io-v2. If a task involves Astro pages, public site assets, marketing Cloudflare deployment, or runtime website APIs, switch to that repository instead of adding the code here.

Docs Content Rules

Only document shipped features; do not add "Coming Soon" sections.
Inside docs/book/, link to sibling pages with relative .md paths.
Link to SDK reference with https://sdkdocs.kitaru.ai.
Link to other ZenML docs with absolute https://docs.zenml.io/... URLs.
Link to diagrams with https://assets.kitaru.ai/docs/diagrams/<slug>.png.
Do not commit temporary planning/review files or prompt exports unless the user explicitly asks for a durable tracked document.
Treat KITARU_* variables as the public configuration surface.
CLI contracts live in src/kitaru/cli/app.py and are available offline through kitaru schema.
The generated OpenAPI document and src/kitaru/api_models/ are the API contract authorities.
Native MCP documentation must match src/kitaru/mcp/registry.py and tests/mcp/snapshots/metrics.json. Run just mcp-schema-check; do not copy tool counts into prose.
The native v2 MCP server does not expose stack or model-alias management.
Do not document v1 runtime surfaces such as kitaru init, kitaru stack, kitaru model, kitaru executions, kitaru.llm(), or kitaru.create_stack() unless they are reintroduced in v2 source and tests.
Agent-facing CLI docs should preserve the structured JSON/JSONL, --machine, --non-interactive, and --no-browser contracts.
Every .mdx page needs title and description frontmatter.

Read the full file on GitHub · 46 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.

7d ago First seen · 46 lines · 13 tokens per session scan A 46bec8696a49

Subscribe to this mod's changes

kitaru-docs is a skill published in the GitHub repository zenml-io/kitaru (280 stars, last pushed yesterday), licensed Apache-2.0. It adds 13 tokens to every session and 848 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.

LLM MLOps Writing and docs ai-agents checkpoints durable-execution mcp

agent-lightning

Provides the action space, tradeoffs, and evaluation context for improving an editable AI agent against a benchmark while preserving its deployment contract. Use when optimizing agent accuracy, cost, latency, or reliability.

microsoft/agent-lightning · 43 tokens

huggingface-hub

HuggingFace hf CLI: search/download/upload models, datasets.

NousResearch/hermes-agent · 20 tokens

healthchain

Use when building, debugging, or deploying a Python service that touches FHIR resources, EHR APIs, CDS Hooks, clinical documents, or patient data — including writing model or agent output back into a patient record, connecting to Epic/Cerner/Medplum, or serving FHIR tools to an agent over MCP or LangChain.

healthchainai/HealthChain · 71 tokens

ai-architect-expert

Expert-level AI system design, MLOps, architecture patterns, and AI infrastructure. Use when the user mentions AI architecture, MLOps, system design, AI infrastructure, or scalability, or when the task involves AI System Architecture, MLOps Infrastructure, Scalability Patterns, or Architecture Design.

personamanagmentlayer/pcl · 66 tokens

ml-expert

Expert-level machine learning, deep learning, model training, and MLOps. Use when the user mentions machine learning, deep learning, neural networks, MLOps, or data science, or when the task involves Machine Learning Fundamentals, Data Preparation, or Model Training.

personamanagmentlayer/pcl · 58 tokens

headless

Autonomer Langlauf-Modus ohne laufende Rückfragen — Startbedingungen (Ziel, Scope, Budgets, Checkpoints), Entscheidungsstufen und Abbruchregeln für unbeaufsichtigte Läufe; erhöht die Ausdauer, nicht die Berechtigung. Nutzen, wenn ausdrücklich ein längerer autonomer Lauf gewünscht ist.

ellmos-ai/skills · 72 tokens

kitaru: Skill for Claude Code