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/dachivadachkoria/claude-code-starter-kit/claude-mdgit clone --depth 1 https://github.com/dachivadachkoria/claude-code-starter-kitWrote 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/dachivadachkoria/claude-code-starter-kit/claude-md)<a href="https://agentmods.dev/instructions/dachivadachkoria/claude-code-starter-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/dachivadachkoria/claude-code-starter-kit/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 5.1 | $0.00992 | $0.00992 |
| Opus 5 | $0.00496 | $0.00496 |
| Sonnet 5 | $0.00198 | $0.00198 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
claude-code-starter-kit 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project: [YOUR PROJECT NAME]
⚠️ Customize this file for your specific project. This is the most important file for Claude Code to understand your codebase.
Overview
[Brief description of what your project does]
Tech Stack
- Language: [Python 3.11+ / TypeScript / Go / etc.]
- Framework: [FastAPI / Express / Gin / etc.]
- Database: [PostgreSQL / MongoDB / etc.]
- Cache: [Redis / Memcached / etc.]
- Testing: [pytest / jest / go test / etc.]
Project Structure
src/ # Source code
├── api/ # API endpoints/routes
├── services/ # Business logic
├── models/ # Data models
├── utils/ # Utilities
tests/ # Test files (mirrors src/ structure)
├── conftest.py # Shared fixtures (Python)
├── unit/ # Unit tests
└── integration/ # Integration tests
docs/ # Documentation
Development Commands
# Install dependencies
[pip install -r requirements.txt / npm install / go mod download]
# Run tests
[pytest tests/ -v / npm test / go test ./...]
# Run with coverage
[pytest --cov=src / npm test -- --coverage / go test -cover ./...]
# Lint
[ruff check . / npm run lint / golangci-lint run]
# Format
[black . && isort . / npm run format / gofmt -w .]
# Start dev server
[uvicorn main:app --reload / npm run dev / go run main.go]
Testing Conventions
File Naming
- Test files:
test_<module>.pyor<module>.test.tsor<module>_test.go - Located in
tests/directory, mirroringsrc/structure
Test Structure
# Python example
def test_<function>_<scenario>_<expected_result>():
# Arrange
...
# Act
...
# Assert
...
Mocking Guidelines
- Mock external services (APIs, databases, cache)
- Use fixtures for common setup
- Never mock the code under test
What to Test
- ✅ Public functions and methods
- ✅ Edge cases and error handling
- ✅ Business logic in services
- ⚠️ Integration points (with mocks)
- ❌ Private implementation details
- ❌ Third-party library internals
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 · 170 lines · 992 tokens per session scan A 6440c2d2814b
claude-code-starter-kit CLAUDE.md is an instructions file published in the GitHub repository dachivadachkoria/claude-code-starter-kit (4 stars, last pushed 6mo ago), licensed MIT. It adds 992 tokens to every session, about $0.0050 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
agents-scaffold AGENTS.md
Instructions for LeeYudok/agents-scaffold, covering agents.md — {{projectname}}, 메모리 경로 오버라이드, .claude/ 인프라, 프로젝트 개요 and 스택.
agents-scaffold CLAUDE.md
Instructions for LeeYudok/agents-scaffold: 이 프로젝트의 가이드·규칙·컨벤션은 AGENTS.md 를 단일 진실원천으로 한다. 아래 import 로 AGENTS.md 내용을 그대로 로드한다.
tailtest CLAUDE.md
Instructions for avansaber/tailtest, covering tailtest, step 0: verify apis before writing test code, step 2: filter -- when to skip, step 3: generate scenarios and step 4: write the test file.
agents-scaffold GEMINI.md
Instructions for LeeYudok/agents-scaffold: 이 프로젝트의 가이드·규칙·컨벤션은 AGENTS.md 를 단일 진실원천으로 한다. 아래 import 로 AGENTS.md 내용을 그대로 로드한다.
ai-rules CLAUDE.md
Claude Code instructions for SpaceMalamute/ai-rules, covering ai rules - multi-target ai tool configurations, structure, principles, adding a technology and git.
AmbyKit CLAUDE.md
Claude Code instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.