Borrowing it
Nothing to install: this file belongs to SawyerHan-AI/TideMind. 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/SawyerHan-AI/TideMind/main/AGENTS.mdgit clone --depth 1 https://github.com/SawyerHan-AI/TideMindWrote 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/sawyerhan-ai/tidemind/agents-md)<a href="https://agentmods.dev/instructions/sawyerhan-ai/tidemind/agents-md"><img src="https://agentmods.dev/badge/instructions/sawyerhan-ai/tidemind/agents-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 | $0.03307 | $0.03307 |
| Opus 5 | $0.01654 | $0.01654 |
| Sonnet 5 | $0.00661 | $0.00661 |
| Haiku 4.5 | $0.00331 | $0.00331 |
Grade A, and why
TideMind AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ExternaBrain 项目规则
开源/闭源架构
本仓库（ExternaBrain）是闭源开发仓库，对应产品品牌 TideMind。pro/ 外全开源，pro/ 内全闭源，无例外。
核心规则：
- 开源代码永远不 import
pro/下的任何东西（反过来可以） - 删除
pro/后，开源版必须能独立编译、运行、通过所有测试 - 永远不要直接修改开源仓库（
~/Projects/tidemind）——所有改动在本仓库进行，通过同步流程推送 - 代码改动：改完后执行
./sync-oss.sh ~/Projects/tidemind同步 - 开源专属文件（README、LICENSE、CONTRIBUTING、docs/）：在
oss-release/下编辑，手动复制到开源仓库 - 用户说"推送 GitHub"时，默认指闭源仓库（ExternaBrain），除非明确说"推送开源仓库"
新增功能归属、Pro 模块加载机制、同步流程、PII 安全见 docs/Codex-guides/oss-sync.md。目录归属表见 docs/Codex-guides/architecture.md。
开发约定
Backlog
开发过程中发现暂时不做但以后要做的事，统一记录到 docs/backlog.md，完成后勾掉并标注日期。格式：- [ ] 描述（发现日期），完成后改为 - [x] 描述 ✅ 已完成（完成日期）。
安装与构建
项目有四套 node_modules：根目录、client/、pro/cloud-server/、pro/website/。fresh clone / 新 worktree 后跑 npm run setup 一键全装；之后改完 src/ 要 npm run build，Electron 客户端才能拿到新代码。
常用命令、安装细节见 docs/Codex-guides/dev-setup.md。运行时数据目录见 docs/Codex-guides/runtime-data.md。
Self-hosted CI
私有 ExternaBrain 当前所有CI job都由Mac Studio承载；公开 TideMind 的CI与双架构发版仍使用GitHub-hosted runner。修改runner labels、workflow路由、隔离、维护或恢复流程前，必须先读 docs/Codex-guides/self-hosted-ci-operations.md。
Stabilization Cycle（2026-04-24 起）
项目进入 2-4 周稳定化重构周期，当前目标是降低回归率，不做完整重写。
本周期内暂停新增大功能：新笔记源、新远程 Agent、新付费计划、新云端代谢策略、新大 UI 页面、大范围视觉重构。允许 P0/P1 bug fix、回归测试、类型修复、lint 修复、CI 增强、局部服务化重构。
改动前后优先运行 npm run health 查看全仓质量状态。client build 和 client typecheck 都是阻塞项。
Feature merge → 必走的 audit subagent 流程（2026-05-20 起）
任何一次包含 ≥1 个新 feature 的 merge 进 main 之前，必须并行派 ≥3 个 Opus subagent 对改动区域做 end-to-end 审计，标出 CRITICAL/HIGH 后才能发版。理由：2026-05-19 / 2026-05-20 两轮事后审计平均每个 feature 找出 14 个潜 bug、3 个 CRITICAL/HIGH，证明"feature 着急上线 → 跳审 → 事后修"的代价比"feature 上线前花 1 小时跑 audit 流程"贵得多。
适用范围：
- 新 feature merge（即便只是 1 个 commit）
- 大重构 / 跨子系统改动
- 安全关键路径（auth / billing / sync / 签名）的任何改动
不适用：纯文档 / 纯依赖升级 / 纯 typo 修复。
执行：见 docs/Codex-guides/release-checklist.md §audit-subagent-protocol。
日志
stdout 保留给 MCP 协议，禁止使用 console.log。 所有日志通过 createLogger 输出到 stderr：
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 Changed · +4 lines · +82 tokens per session 87c2d62940ba
- 7d ago First seen · 137 lines · 3,225 tokens per session scan A e3e76857f1ba
TideMind AGENTS.md is an instructions file published in the GitHub repository SawyerHan-AI/TideMind (9 stars, last pushed 4d ago), licensed MIT. It adds 3,307 tokens to every session, about $0.0165 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
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).
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.
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).
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.