What is kitaru AGENTS.md?

Repository instructions for kitaru, a software project containing a Python package, server, software development kit, examples, and documentation. They describe the project layout, coding practices, and testing guidance.

Use them when working on kitaru's Python code, server, SDK, examples, documentation, scripts, tests, adapters, or releases.

They give a coding agent the project context and local rules needed to make changes in the right files and verify them appropriately.

How zenml-io/kitaru configures Codex and OpenCode

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.md

Clone the repo

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

Made for: Codex, OpenCode.

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/instructions/zenml-io/kitaru/agents-md/github.svg)](https://agentmods.dev/instructions/zenml-io/kitaru/agents-md)

Your own site

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

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/zenml-io/kitaru/agents-md"><img src="https://agentmods.dev/badge/instructions/zenml-io/kitaru/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,227 This file is loaded in full into every session.

When invoked 2,227 The same file — it is already loaded in full.

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	$0.02227	$0.02227
Opus 5.5	$0.00891	$0.00891
Sonnet 5.5	$0.00445	$0.00445
Haiku 4.5	$0.00223	$0.00223

Measured 3d ago against content hash 09398b0da6bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kitaru AGENTS.md 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.

AGENTS.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Kitaru is a mixed Python + docs repo. It produces the Python package (SDK and server) and the SDK reference docs app. The public marketing site and kitaru.ai runtime live in the sibling zenml-io-v2 repository, not here.

Positioning surfaces (README, docs leads, PyPI description) lead with insights, in the Kitaru product page's four steps: bring your traces, get insights across every session, turn findings into checks, and replay a fix before it ships. Replay is how a fix gets tested, not the headline.

Project Map

src/kitaru/: Python package (src layout); see src/kitaru/AGENTS.md
src/kitaru/api_models/: versioned request/response DTOs shared by server and SDK
src/kitaru/client/: async SDK making REST calls
src/kitaru/server/: FastAPI server (API, application, domain, adapters layers)
tests/: pytest suite; see tests/AGENTS.md when working there
examples/: runnable SDK examples, grouped as python/ and typescript/
docs/book/: hand-written GitBook docs; see docs/book/AGENTS.md
docs/content/docs/: generated SDK reference content
docs/app/, docs/scripts/, docs/worker/: reference app, generation, and redirect worker code
scripts/: OpenAPI generation, doc generation, and UI bundle scripts
docker/: Dockerfiles
design/: gitignored design notes; never commit anything from this directory

For adapter, importer, specialized UI API, docs, CI, and release work, load the matching Kitaru repo skill under .agents/skills/. Keep each logical repo skill available under the same name in .claude/skills/; share host-neutral guidance and diverge only for a documented host-specific reason.

Before editing a subtree, read the AGENTS.md files along its path that have not already been loaded. If a directory has no AGENTS.md but has a CLAUDE.md, read that guidance too.

Task scope and follow-through

Complete the work authorized by the user's request, including relevant verification and final review. Make reasonable assumptions for routine choices and continue independent authorized work while a material decision is pending. Task skills guide execution; they do not independently authorize commits, publication, or release actions. Do not ask again for an action already authorized in the conversation.

Read the full file on GitHub · 119 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.

3d ago Changed · +2 lines · +63 tokens per session 09398b0da6bb
7d ago Changed · -28 lines · -32 tokens per session 8d567154b557
8d ago Changed · +1 lines · +146 tokens per session 64236ae40622
1mo ago Changed · -4 lines · -30 tokens per session 5ce201a5d7c8
2mo ago Changed · +13 lines · +376 tokens per session 35e8e75b7d38
2mo ago Changed · +1 lines · +16 tokens per session aa46a8c6dda8
2mo ago First seen · 134 lines · 1,688 tokens per session scan A 1be293601629

Subscribe to this mod's changes

kitaru AGENTS.md is an instructions file published in the GitHub repository zenml-io/kitaru (317 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,227 tokens to every session, about $0.0089 per session on Opus 5.5. 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 ai-agents checkpoints durable-execution mcp

kitaru AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
kitaru AGENTS.mdzenml-io/kitaru	Instructions file	317	yesterday	Apache-2.0	A	2,227	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

kitaru: Instructions file for Codex