What is krozov-ai-tools CLAUDE.md?

A Claude Code instruction file for krozov-ai-tools, defining project rules, plugin standards, publishing safeguards, and language requirements.

Use it when changing plugins, checking release readiness, synchronizing versions, or following repository publishing rules.

It helps agents avoid release mistakes and keep plugin versions and shipped content consistent.

How kirich1409/krozov-ai-tools configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kirich1409/krozov-ai-tools. 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/kirich1409/krozov-ai-tools/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kirich1409/krozov-ai-tools

Made for: Claude Code.

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/kirich1409/krozov-ai-tools/claude-md/github.svg)](https://agentmods.dev/instructions/kirich1409/krozov-ai-tools/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/kirich1409/krozov-ai-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/kirich1409/krozov-ai-tools/claude-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/kirich1409/krozov-ai-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/kirich1409/krozov-ai-tools/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,576 This file is loaded in full into every session.

When invoked 1,576 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 94% copy Near-identical to another mod 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	$0.01576	$0.01576
Opus 5.5	$0.00630	$0.00630
Sonnet 5.5	$0.00315	$0.00315
Haiku 4.5	$0.00158	$0.00158

Measured 1mo ago against content hash b20750283bb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

krozov-ai-tools CLAUDE.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.

Origin

This is a copy

94% identical to krozov-ai-tools AGENTS.md — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Non-negotiables

Rules that are not open for discussion. Violating these is an error, not a judgment call.

Never run npm publish locally. Publishing is exclusively via GitHub Actions — prevents partial releases and version skew.
All 3 version locations of a plugin must stay in sync. Each plugin carries its version in three places, and a bump touches all three of that plugin simultaneously — the other plugin is not touched. See Publishing for the per-plugin list.
Critical or Major violations of PLUGIN-STANDARDS.md block the release. Fix first, release later.
All extension content is written in English. Skills (SKILL.md, references, evals), agents (agents/*.md), hooks, MCP servers, plugin manifests (plugin.json, marketplace.json), and any prompt/instruction text shipped inside plugins/ must be in English. User-facing chat in any language is fine; the shipped extension content itself targets an international audience and must not contain non-English prose. Code identifiers and external API field names keep their original form regardless of language. Excluded: repository documentation under docs/ and top-level README.md — these are maintainer-facing and may be in any language. Do not "fix" them to English.

Project

Monorepo for Claude Code plugins by krozov. Contains one plugin. maven-mcp moved to https://github.com/kirich1409/maven-mcp and is not installed from this repository.

Plugin	Directory	Description
youtube-transcript	`plugins/youtube-transcript/`	MCP server that fetches existing YouTube subtitles via the InnerTube API

Structure

plugins/
  youtube-transcript/           # Python MCP server (stdlib only, zero pip deps)

See the plugin's own CLAUDE.md for plugin-specific instructions.

Plugins are isolated. This is a shared home for multiple independent plugins, not a monolith with unified internals. A convention, pattern, or design decision that fits one plugin (module layout, error-handling style, a specific caching or retry strategy, dependency choices) is scoped to that plugin — do not migrate it into another plugin just because both live in this repo. Evaluate each plugin's own requirements on their own terms; cross-plugin consistency is not a goal here.

Read the full file on GitHub · 83 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.

1mo ago Changed · -3 lines · -82 tokens per session b20750283bb8
2mo ago First seen · 86 lines · 1,658 tokens per session scan A a8a0f670028a

Subscribe to this mod's changes

krozov-ai-tools CLAUDE.md is an instructions file published in the GitHub repository kirich1409/krozov-ai-tools (23 stars, last pushed 1mo ago), licensed MIT. It adds 1,576 tokens to every session, about $0.0063 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to krozov-ai-tools AGENTS.md, differing in 10 lines, and is treated as a copy.

Git and workflow Project management Releases

krozov-ai-tools CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
krozov-ai-tools CLAUDE.mdkirich1409/krozov-ai-tools	Instructions file	23	1mo ago	MIT	A	1,576	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	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

krozov-ai-tools: Instructions file for Claude Code