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/leihuang830102-hash/opencode-howto/claude-mdgit clone --depth 1 https://github.com/leihuang830102-hash/Opencode-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/leihuang830102-hash/opencode-howto/claude-md)<a href="https://agentmods.dev/instructions/leihuang830102-hash/opencode-howto/claude-md"><img src="https://agentmods.dev/badge/instructions/leihuang830102-hash/opencode-howto/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 | $0.01747 | $0.01747 |
| Opus 5 | $0.00873 | $0.00873 |
| Sonnet 5 | $0.00349 | $0.00349 |
| Haiku 4.5 | $0.00175 | $0.00175 |
Grade A, and why
Opencode-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 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to OpenCode when working with code in this repository.
Project Overview
OpenCode Howto — 基于 Claude Code Howto 中文版（上游在 claude-howto-zh-cn-main/）适配的 OpenCode 内部培训教程。核心机制是通过 OpenCode 对话窗口中的 skills（自测 + 模块测验）引导用户从自我评估到分阶段学习 10 个功能模块。
详细项目需求见 PROJECT_OVERVIEW.md。
Build / Test / Lint Commands
Python 脚本在 scripts/ 目录，需要 uv 包管理器。
# 开发环境
uv venv && uv pip install -r scripts/requirements-dev.txt
# EPUB 构建
uv run scripts/build_epub.py --root . --output output.epub --verbose
# 测试
uv run pytest scripts/tests/ -v # 全部
uv run pytest scripts/tests/test_validate_localization.py -v # 单文件
uv run pytest scripts/tests/test_validate_localization.py::test_validate_markdown_links_detects_missing_file -v # 单函数
# Lint & 格式化
uv run ruff format scripts/ # 格式化
uv run ruff check --fix scripts/ # lint 修复
uv run bandit -c scripts/pyproject.toml -r scripts/ --exclude scripts/tests/ # 安全扫描
# 本地化验证
uv run python scripts/validate_localization.py
# Pre-commit
pre-commit run --all-files
Architecture: Two-Layer Structure
根目录 (OpenCode 适配层)
├── 01-slash-commands/ ... 10-cli/ # 10 个教程模块（从上游复刻+适配）
├── .opencode/skills/ # OpenCode skills（自测 + 模块测验）
├── AGENTS.md # OpenCode 项目配置（等同 CLAUDE.md）
├── scripts/ # Python 工具脚本（从上游复刻）
│
└── claude-howto-zh-cn-main/ # 上游参考（只读，不修改）
├── .claude/skills/ # Claude 版 skills
├── .github/workflows/ # CI 配置
└── * # 原始内容
核心规则：claude-howto-zh-cn-main/ 是只读上游参考。所有 OpenCode 适配工作在根目录进行。
Term Mapping: Claude Code → OpenCode
根目录文件中所有 Claude Code 专属术语必须替换为 OpenCode 对应术语：
| Claude Code | OpenCode | 说明 |
|---|---|---|
CLAUDE.md |
AGENTS.md |
项目配置文件 |
.claude/skills/ |
.opencode/skills/ |
技能目录 |
.claude/commands/ |
.opencode/commands/ |
自定义命令 |
.claude/agents/ |
.opencode/agents/ |
子代理目录 |
claude (CLI 命令) |
opencode |
CLI 入口 |
claude -p |
opencode run |
Non-interactive mode (子命令) |
~/.claude/ |
~/.config/opencode/ |
用户配置目录 |
settings.json |
opencode.json |
配置文件名 |
mcpServers |
mcp |
MCP 配置 key |
AskQuestion |
question |
用户问答工具 |
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 · 139 lines · 1,747 tokens per session scan A 80b44c1a06da
Opencode-Howto CLAUDE.md is an instructions file published in the GitHub repository leihuang830102-hash/Opencode-Howto (5 stars, last pushed 4mo ago), licensed MIT. It adds 1,747 tokens to every session, about $0.0087 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
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.
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.