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/zhmxiaowo/opencode-simple/claude-mdgit clone --depth 1 https://github.com/zhmxiaowo/opencode-simpleWhat 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 | $0.00881 | $0.00881 |
| Opus 5 | $0.00441 | $0.00441 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
opencode-simple 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 2d 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 — OpenCode Simple (CDD & Spec-First)
本文件为 Claude Code AI 编程助手提供项目指导。（OpenCode 使用 AGENTS.md）
项目概述
这是一个基于 ECC (Everything Claude Code) 架构的纯粹 CDD（编译驱动开发）& Spec-First 通用编程框架。
核心哲学：
- 🚫 绝对禁止 TDD — 不写任何测试代码
- 📋 Spec 先行 — 无 SPEC.md 不编码
- ⚙️ 编译驱动 — Exit Code 0 + LSP 0 Error = 任务完成
- 🧠 Think Before Fix — 编译错误必须用 sequential-thinking 分析
架构
核心组件
.opencode/agents/— 精简的 Agent 团队（planner, architect, build-error-resolver, code-reviewer 等）.opencode/skills/— 通用工作流知识（CDD 验证、蓝图规划、持续学习 V2 等）.opencode/commands/— 用户命令（/spec, /plan, /build-fix, /verify, /learn 等）rules/common/— 永远遵守的准则（CDD 核心、编码风格、安全）hooks/— 异步 Hooks（会话持久化、上下文防腐烂、持续学习观测）scripts/— 跨平台 Node.js 工具脚本（hooks 和 setup 用）mcp-configs/— MCP 配置参考文件
核心 MCP 矩阵（仅 5 个）
| MCP | 用途 |
|---|---|
exa-web-search |
全网搜索代码和报错 |
context7 |
查阅最新官方文档防幻觉 |
mcp-language-server |
本地 LSP 诊断（CDD 核心） |
memory |
跨会话记忆 |
sequential-thinking |
编译错误链式推理 |
关键命令
| 命令 | 说明 |
|---|---|
/plan |
Spec-First + 实施计划: MCP 研究 → SPEC → 步骤分解（编码前必须执行） |
/spec |
/plan 的轻量版，只输出 SPEC 不输出步骤 |
/build-fix |
CDD 修复编译错误 |
/verify |
CDD 验证（编译+LSP+AI slop 检查，无测试） |
/code-review |
代码审查（无测试覆盖率要求） |
/handoff |
结构化会话交接（CDD 状态、SPEC 进度、决策记录） |
/learn |
从会话中提取可复用模式 |
/evolve |
将 instincts 进化为 skills/commands |
工作流
意图分类 → /plan [功能] → SPEC + 步骤 → 用户确认 → 编码 → /build-fix → /verify → /code-review → /handoff
保留的 ECC 神级机制
- V2 本能学习 (Continuous Learning) — 自动从会话中提取编译错误模式
- 异步 Hooks — 防止上下文腐烂，自动保存会话状态
- Memory MCP — 跨会话记忆，记录项目上下文
- Sequential Thinking — 编译错误时的强制链式推理
禁止事项
- ❌ 不要编写任何测试文件
- ❌ 不要引用 Jest/Vitest/pytest 等测试框架
- ❌ 不要以"缺少测试"为由阻塞代码审查
- ❌ 不要在没有 SPEC.md 的情况下开始编码
- ❌ 不要在编译错误时盲目试错（必须先 think）
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.
- 2d ago First seen · 70 lines · 881 tokens per session scan A 432c1a908df1
opencode-simple CLAUDE.md is an instructions file published in the GitHub repository zhmxiaowo/opencode-simple (2 stars, last pushed 5mo ago), licensed MIT. It adds 881 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 2026-08-31.
Other instructions, from other repositories
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.
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.