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.
npx agentmods add instructions/ruslan-korneev/claude-plugins/claude-mdgit clone --depth 1 https://github.com/ruslan-korneev/claude-pluginsWrote 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/ruslan-korneev/claude-plugins/claude-md)<a href="https://agentmods.dev/instructions/ruslan-korneev/claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/ruslan-korneev/claude-plugins/claude-md.svg" alt="Measured on agentmods" 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 | $0.00738 | $0.00738 |
| Opus 5 | $0.00369 | $0.00369 |
| Sonnet 5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
claude-plugins 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 5d 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 — 92 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.
What is This
A collection of Claude Code plugins for Python backend development (FastAPI + SQLAlchemy 2.0 + uv).
Commands
# Validate all plugins (run before committing)
python .github/scripts/validate_plugins.py
# Add local marketplace for testing
/plugin marketplace add ./
# Install specific plugin
/plugin install {plugin-name}@python-backend-plugins
Repository Structure
├── plugins/ # 3 consolidated plugins
│ ├── python/ # Linting, typing, clean code, TDD
│ ├── fastapi/ # FastAPI scaffolding + Alembic migrations
│ └── tech-lead/ # Architecture, review, dev cycles, features
├── external_plugins/ # Third-party plugins
├── .claude-plugin/
│ └── marketplace.json # Central plugin catalog
└── .github/scripts/
└── validate_plugins.py # CI validation script
Plugins
| Plugin | Purpose | Key Commands |
|---|---|---|
| python | Linting, typing, clean code, TDD | /lint, /typecheck, /clean:review, /test:first |
| fastapi | FastAPI scaffolding + Alembic | /module, /dto, /endpoint, /migrate:create |
| tech-lead | Architecture, review, dev cycles, features | /design, /review, /dev, /features:init |
Core Principles
- ZERO noqa / ZERO type:ignore — always fix properly, never suppress
- TDD — test first, then implementation
- TypedDict > dict[str, Any] — strict dictionary typing
- Real test database — never mock the database
- Branch coverage — more important than line coverage
Commit Convention
# Format: <type>(<plugin>): <description>
feat(python): add support for RUF100 rule
fix(fastapi): correct migration enum handling
docs(tech-lead): update architecture review examples
Types: feat, fix, docs, chore, refactor, test
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.
- 5d ago First seen · 92 lines · 738 tokens per session scan A 9591382952d1
claude-plugins CLAUDE.md is an instructions file published in the GitHub repository ruslan-korneev/claude-plugins (4 stars, last pushed 6mo ago), licensed MIT. It adds 738 tokens to every session, about $0.0037 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 2026-08-31.
Other instructions, from other repositories
claude-ai-music-skills CLAUDE.md
Claude Code instructions for bitwize-music-studio/claude-ai-music-skills, covering ai music skills - claude instructions, ⚠️ critical: finding albums when user mentions them, configuration & path resolution, mcp server — preferred data access and session start.
claude-plugins CLAUDE.md
Claude Code instructions for AleksandarBisevac/claude-plugins, covering working on this repo, hard rules, adding a .py under hooks/ or scripts/, which skill covers what and the front end is not ordinary files.
octopus CLAUDE.md
Claude Code instructions for SatoruoGojoo/octopus, covering claude.md, 這個 repo 是什麼, 權威來源與修改順序, 版更收尾紀律（版號提升前必跑） and 檔案結構與各檔職責.
stem AGENTS.md
Instructions for markskrypka/stem, covering stem.cooking, commands, invariants and current state.
agentic-ml-plugin AGENTS.md
AGENTS.md instructions for lawwu/agentic-ml-plugin, covering agentic ml skills, keep updated, changelog conventions, structure and creating a skill.
stem CLAUDE.md
Instructions for markskrypka/stem, a project described as: Engineering discipline for coding agents: size the work, keep every change on the record, verify against intent, never lose a session. Works in Claude Code, Codex, Cursor, and Gemini CLI.