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/humzakt/dev-starter-kit/claude-mdgit clone --depth 1 https://github.com/humzakt/dev-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/humzakt/dev-starter-kit/claude-md)<a href="https://agentmods.dev/instructions/humzakt/dev-starter-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/humzakt/dev-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 | $0.00469 | $0.00469 |
| Opus 5 | $0.00234 | $0.00234 |
| Sonnet 5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
dev-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 3d 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.
What it actually says
CLAUDE.md — Instructions for Claude Code
Claude reads this file at the start of every session. Keep it concise and actionable.
Commands
# Lint
ruff check . && ruff format --check .
# Fix lint
ruff check --fix . && ruff format .
# Test
pytest tests/ -v
# Test single file
pytest tests/test_<module>.py -v
# Pre-commit
pre-commit run --all-files
Code Style
- Python 3.11+, Ruff for linting/formatting (config in pyproject.toml)
- 120 char line length, double quotes, Google-style docstrings
- Type hints on all public function signatures
- Specific exception handling (no bare
except:) pathlib.Pathoveros.path, f-strings over.format()
Testing Rules
- Tests in
tests/test_<module>.py, classesTest<ModuleName>, methodstest_<func>[_<scenario>] - Mock external dependencies — no real network calls in tests
- Every source change needs a corresponding test change (CI enforced)
- Run
pytest tests/ -vafter every change
Workflow
- Read relevant files before editing
- Make minimal, focused changes
- Run
ruff check --fix . && ruff format .after every edit - Run
pytest tests/ -vto verify - If tests fail, fix them before moving on
- Use conventional commits:
feat:,fix:,chore:,docs:,test:,refactor:
Architecture
src/— source codetests/— tests (mirrors src/ structure)docs/— documentationpyproject.toml— ruff + pytest config.github/workflows/— CI/CD
Don'ts
- Don't commit .env files or secrets
- Don't skip tests — CI will catch it
- Don't commit directly to main — branch protection is on
- Don't add unnecessary comments that just narrate what code does
- Don't create files unless absolutely necessary — prefer editing existing ones
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.
- 3d ago First seen · 63 lines · 469 tokens per session scan A 325914388033
dev-starter-kit CLAUDE.md is an instructions file published in the GitHub repository humzakt/dev-starter-kit (3 stars, last pushed 6mo ago), licensed MIT. It adds 469 tokens to every session, about $0.0023 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
deepagents AGENTS.md
AGENTS.md instructions for langchain-ai/deepagents, covering global development guidelines for the deep agents monorepo, corridor security analysis, development workflow, suppressing ruff rules and pr conventions.
apm python.instructions.md
Python development guidelines.
Embody AGENTS.md
AGENTS.md instructions for dylanroscover/Embody, covering embody + envoy - ai instructions, critical rules, td python rules, network layout rules and mcp server safety rules.
windmill AGENTS.md
AGENTS.md instructions for windmill-labs/windmill, covering windmill, workflow, documentation, dev environment and per-worktree ports and database.
lobster0 AGENTS.md
AGENTS.md instructions for NEDONION/lobster0, covering lobster0 agent 工程规范, 适用范围与优先级, 项目事实, 常用命令 and 首次安装或依赖变化后.
streamlit e2e_playwright.instructions.md
Instructions for streamlit/streamlit, covering streamlit e2e tests, test structure, key fixtures and utilities, external test mode and url handling (no localhost hardcoding).