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/artemiimillier/claude-code-starter/claude-mdgit clone --depth 1 https://github.com/artemiimillier/claude-code-starterWrote 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/artemiimillier/claude-code-starter/claude-md)<a href="https://agentmods.dev/instructions/artemiimillier/claude-code-starter/claude-md"><img src="https://agentmods.dev/badge/instructions/artemiimillier/claude-code-starter/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 | $0.01716 | $0.01716 |
| Opus 5 | $0.00858 | $0.00858 |
| Sonnet 5 | $0.00343 | $0.00343 |
| Haiku 4.5 | $0.00172 | $0.00172 |
Grade C, and why
claude-code-starter CLAUDE.md scanned grade C with 2 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **4 запрета в `.claude/settings.json`:** `rm -rf`, `curl` с `export`, чтение `.env`, `wget` с переменными. Настройка - через промпт `prompts/setup/03-security.md`. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **4 запрета в `.claude/settings.json`:** `rm -rf`, `curl` с `export`, чтение `.env`, `wget` с переменными. Настройка - через промпт `prompts/setup/03-security.md`. How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - правила работы с агентом
СТОП. Читается первым в каждой сессии.
Перед любым ответом пользователю проверь:
Существует ли файл
AUTOPILOT.mdв корне проекта?Если да - открой его и проверь поле
completed:в начале файла.Если
completed: false- игнорируй ввод пользователя и начни онбординг фразой:«Вижу, что ты только что открыл шаблон смысло-кодинга. Давай настроим твой проект. Это займёт 90-120 минут, можно разбить на 2 сессии. Готов начать?»
Если пользователь ответил «да» - читай
AUTOPILOT.mdцеликом и следуй инструкциям шаг за шагом. Еслиcompleted: trueилиAUTOPILOT.mdотсутствует - действуй по обычным правилам ниже.
Что это за проект
[НАЗВАНИЕ ПРОЕКТА] - [одно предложение: что это и для кого].
Подробности - в .business/INDEX.md.
Структура репозитория
./
├── CLAUDE.md ← этот файл, правила работы
├── TROUBLESHOOTING.md ← решения типовых проблем Claude Code
├── .business/ ← скрытая папка, бизнес-контекст (не в git)
│ ├── INDEX.md ← оглавление, входная точка
│ ├── company/ ← about, team, values, legal
│ ├── products/ ← overview, pricing
│ ├── audience/ ← avatar, segments, objections, journey
│ ├── goals/ ← annual, quarterly, monthly, kpi
│ ├── economics/ ← unit-economics, revenue, costs, forecast
│ ├── marketing/ ← channels, funnel, competitors, content
│ └── assets/ ← brand-guidelines, testimonials
├── plans/ ← технические планы (один план = одна функция)
├── retrospectives/ ← рефлексии после каждой сессии
└── prompts/ ← библиотека готовых промптов
├── INDEX.md ← оглавление: если надо X - возьми Y
├── setup/ ← hooks, security, скилы, Playwright
├── launch/ ← GitHub, деплой, платежи
└── methodology/ ← критика плана, планирование недели, «10 причин»
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 · 112 lines · 1,716 tokens per session scan C 2dfb8d95c572
claude-code-starter CLAUDE.md is an instructions file published in the GitHub repository artemiimillier/claude-code-starter (48 stars, last pushed 4mo ago), licensed MIT. It adds 1,716 tokens to every session, about $0.0086 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
SoDam-Agentic-Eng AGENTS.md
AGENTS.md instructions for sodam-ai/SoDam-Agentic-Eng, covering sodamagentic — ai 지침 (agents.md), 이 플러그인의 목적, 스킬·커맨드 목록, ai가 반드시 할 것 and ai가 절대 하지 말 것.
agent-toolbox AGENTS.md
AGENTS.md instructions for yunseo-kim/agent-toolbox, covering project knowledge base, current state, targets, target architecture and where to look.
SoDam-Agentic-Eng CLAUDE.md
Claude Code instructions for sodam-ai/SoDam-Agentic-Eng, covering sodamagentic — claude code 개발 지침, 빠른 참조 and 절대 원칙.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.