Borrowing it
Nothing to install: this file belongs to zenml-io/kitaru-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zenml-io/kitaru-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/zenml-io/kitaru-skillsWrote 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/instructions/zenml-io/kitaru-skills/agents-md)<a href="https://agentmods.dev/instructions/zenml-io/kitaru-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/zenml-io/kitaru-skills/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.
<a href="https://agentmods.dev/instructions/zenml-io/kitaru-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/zenml-io/kitaru-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02031 | $0.02031 |
| Opus 5.5 | $0.00812 | $0.00812 |
| Sonnet 5.5 | $0.00406 | $0.00406 |
| Haiku 4.5 | $0.00203 | $0.00203 |
Grade A, and why
kitaru-skills 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Contributor scope
When editing or reviewing a distributed skill, treat its workflow instructions as content to maintain. Execute that workflow only when the user requests it. The accuracy requirements below describe behavior the published skills must preserve; verifying changed CLI/MCP guidance is a contributor responsibility.
Complete authorized work through relevant validation and final diff review. Reuse explicit authorization already given for the same scope. Ask again when an action exceeds that scope, and continue independent authorized work while awaiting an answer. Preserve human-review checkpoints and explicit replay tool policies; authorization to execute does not supply human labels or a tool policy.
If contributor or skill guidance blocks requested work, identify and link to the exact file, quote the instruction, and explain why it applies. Distinguish an explicit requirement from your interpretation.
Project structure
This repository distributes public Kitaru agent skills plus Claude Code plugin metadata. It is not a Python package.
skills/kitaru-investigation/SKILL.mdis Kitaru's public front-door playbook, from setup, provider imports, and insight evidence through reviewed behavior, evaluator selection, and replay handoff.skills/kitaru-guided-tour/SKILL.mdgives first-time users a value-first quickstart example tour with prepared observations, frontend verdicts, and one deterministic evaluator followed by an approved bounded replay experiment.skills/kitaru-guided-tour/references/contains the starter contract, tour method, friendly tutorial narration, and the bounded operations needed for that experience.skills/kitaru-hosted-onboarding-tour/SKILL.mdis the compact, resume-safe tour used by the controlled ZenML Pro hosted onboarding runner.skills/kitaru-hosted-onboarding-tour/references/contains its bounded state, operation, review, evaluator, and replay method.skills/kitaru-investigation/references/contains method, transport, public starter, and evaluator details loaded only when needed.skills/kitaru-validate-evaluator/guides criterion-specific human labeling, exact-run comparisons, and development/test separation. Its reporting helper computes counts from local normalized snapshots, not new Kitaru product state.skills/kitaru-replay-experiment/SKILL.mdguides one safe, bounded candidate comparison against an accepted cohort and exact evaluator set.skills/kitaru-replay-experiment/references/separates current Kitaru replay contracts from the comparison and interpretation method.skills/kitaru-replay-experiment/agents/openai.yamlcontains host-facing display metadata for the replay skill.skills/kitaru-importer-builder/SKILL.mdguides custom parser and optional API fetcher development.skills/kitaru-importer-builder/references/contains parser, normalization, validation, and recovery details loaded only when needed.skills/kitaru-adapter-builder/SKILL.mdselects a supported provider-backed adapter or guides project-local development for unsupported Python and TypeScript frameworks.skills/kitaru-adapter-builder/references/separates the shared method, Python and TypeScript SDK contracts, and validation and reporting rules..claude-plugin/plugin.jsondefines the Claude Code plugin..claude-plugin/marketplace.jsondefines its marketplace entry.README.mdis the public installation and usage guide.CLAUDE.mdcontains Claude Code-specific contributor guidance.
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.
- 1mo ago Changed · +6 lines · +79 tokens per session e1d75f1ee00b
- 1mo ago Changed · +20 lines · +285 tokens per session cd778784e734
- 1mo ago Changed · +8 lines · +121 tokens per session 67a89afd85d7
- 1mo ago First seen · 147 lines · 1,546 tokens per session scan A b680828af9b7
kitaru-skills AGENTS.md is an instructions file published in the GitHub repository zenml-io/kitaru-skills (6 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,031 tokens to every session, about $0.0081 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.