luongnv89/claude-howto is a visual, example-based guide to Claude Code, a coding tool that supports agents, hooks, skills, slash commands, and MCP servers. Developers use it to learn Claude Code through practical workflows and copyable templates, including the commands, agents, skills, plugins, and instructions catalogued here.
Borrowing it
Nothing to install: this file belongs to luongnv89/claude-howto. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/luongnv89/claude-howto/main/CLAUDE.mdgit clone --depth 1 https://github.com/luongnv89/claude-howtoWrote 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/luongnv89/claude-howto/claude-md)<a href="https://agentmods.dev/instructions/luongnv89/claude-howto/claude-md"><img src="https://agentmods.dev/badge/instructions/luongnv89/claude-howto/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.
<a href="https://agentmods.dev/instructions/luongnv89/claude-howto/claude-md"><img src="https://agentmods.dev/badge/instructions/luongnv89/claude-howto/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00883 | $0.00883 |
| Opus 5 | $0.00441 | $0.00441 |
| Sonnet 5 | $0.00177 | $0.00177 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
claude-howto 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 10d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Tutorial repo. Output is markdown in numbered modules 01- through 10-, not an app. Scripts in scripts/ exist only to validate docs and build the EPUB.
See also .claude/CLAUDE.md for stack/commands and STYLE_GUIDE.md for lesson structure.
Critical commands
# Quality gate (also runs on commit via pre-commit hooks)
pre-commit run --all-files
# Tests
pytest scripts/tests/ -v
# EPUB build (renders Mermaid with the local mmdc CLI — no network, needs mmdc on PATH)
uv run scripts/build_epub.py
# Python tooling
ruff check scripts/ && ruff format scripts/
mypy scripts/ --ignore-missing-imports
bandit -c scripts/pyproject.toml -r scripts/ --exclude scripts/tests/
Pre-commit runs 5 doc checks on .md changes: markdown-lint, cross-references, mermaid-syntax, link-check, markdown-rendering. All must pass. The EPUB build is not a pre-commit hook — it runs in CI only (build-epub job in .github/workflows/test.yml), because it needs a local mmdc binary that has no working arm64 build.
Architecture map
01-…10-— tutorial modules. Numbered prefix = learning order, not alphabetical. Do not reorganize.- Each module:
README.md+ copy-paste templates (.md,.json,.sh). scripts/— utilities (EPUB builder, link/mermaid/cross-ref validators). Not the product.02-memory/*.md— CLAUDE.md templates users copy into their own projects. Don't confuse with this file.openspec/— spec-driven change proposals.
Hard rules
- YOU MUST NOT commit or push without explicit user request.
- YOU MUST NOT add
Co-Authored-By: Claudeto any commit message. - Always activate
.venvbefore running Python scripts (checkvenv/,.venv/,env/). - Internal links use relative paths (e.g.
01-slash-commands/README.md); anchors use#heading-name. - Code fences must declare a language (
bash,python,json, …) — the cross-reference check fails otherwise. - External URLs must be reachable and stable. No ephemeral links.
- Mermaid diagrams must parse (validated pre-commit, and only when
mmdcis installed — the check skips with a warning otherwise). A broken EPUB build is usually invalid Mermaid or a missing/failingmmdc. - Commit format:
type(scope): subjectwherescopematches the module folder (e.g.feat(slash-commands):,docs(memory):,fix(README):). - Do not reorganize the
01-–10-numbering. The order is the curriculum.
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.
- 10d ago First seen · 63 lines · 883 tokens per session scan A 035a4879fe9b
claude-howto CLAUDE.md is an instructions file published in the GitHub repository luongnv89/claude-howto (41,418 stars, last pushed 3d ago), licensed MIT. It adds 883 tokens to every session, about $0.0044 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 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.