Borrowing it
Nothing to install: this file belongs to zai-org/Synapse. 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/zai-org/Synapse/main/AGENTS.mdgit clone --depth 1 https://github.com/zai-org/SynapseWrote 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/zai-org/synapse/agents-md)<a href="https://agentmods.dev/instructions/zai-org/synapse/agents-md"><img src="https://agentmods.dev/badge/instructions/zai-org/synapse/agents-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/zai-org/synapse/agents-md"><img src="https://agentmods.dev/badge/instructions/zai-org/synapse/agents-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 | $0.05342 | $0.05342 |
| Opus 5.5 | $0.02137 | $0.02137 |
| Sonnet 5.5 | $0.01068 | $0.01068 |
| Haiku 4.5 | $0.00534 | $0.00534 |
Grade A, and why
Synapse AGENTS.md scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl -sS http://127.0.0.1:3001/api/v1/health` How it starts
The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
当前系统处于初期设计实现阶段，不要考虑兼容旧数据。
系统分层架构（DB / DTO / Wire 边界）
完整背景与执行计划见 docs/architecture-boundary-refactor-master-plan.md。 本节是编码时必须遵守的规范；guard 脚本会强制其中可机检的条目。
三个命名世界，由「层」决定，不由「包」决定
- PostgreSQL = snake_case：物理表/列保持 snake_case，是持久化真源。
- TypeScript 业务层 = camelCase：Kysely 装了
CamelCasePlugin({ maintainNestedObjectKeys: true })，row 在 TS 侧顶层标识符全部 camelCase（row.workspaceId，不是row.workspace_id）。 - Wire / machine = snake_case：
packages/device-protocol的签名封套、pairing、control-plane、reverse-MCP 故意保持 snake_case；这些 key 参与 Ed25519 签名规范化，绝不能改名。
snake_case 出现在两种地方：(a) DB 物理层与 device-protocol wire 契约——合法；(b) packages/api/src/modules/** 的 service/controller 或 packages/web-next 的组件里——禁止，那是 DB row 泄漏。
七层职责（modules// 内）
| 层 | 文件 | 只能做 | 禁止 |
|---|---|---|---|
| repo | repo.ts / repo.types.ts |
SQL、join、projection、business JSON 解码(Zod)；产出 XxxRecord(camelCase) |
输出 app DTO / wire payload |
| service | service.ts |
业务流程、用例编排 | import generated/db、用 TableRow、拼 HTTP envelope、做 wire 序列化 |
| presenter | presenter.ts |
域记录 → app DTO；Date→IsoInstantString、fileId→URL、显示派生 |
SQL、事务、业务前置 JSON 校验、wire payload |
| wire-adapter | wire.ts |
域记录 ↔ snake_case wire；用 device-protocol schema；签名/裸 payload 组装 | SQL、业务流程、app DTO |
| controller | controller.ts |
zod parse → service → presenter/wire → 发送 | 直接访问 row |
| schemas | schemas.ts |
路由本地 zod（path/query 拼装） | 重新定义对外契约类型——app 请求体/响应 DTO 均 import 自 shared |
| index | index.ts |
fastify-plugin + app.register(controller, { prefix }) |
业务逻辑 |
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.
- 1mo ago First seen · 172 lines · 5,342 tokens per session scan A 1ae68460f4f0
Synapse AGENTS.md is an instructions file published in the GitHub repository zai-org/Synapse (488 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 5,342 tokens to every session, about $0.0214 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
plan-forge caching.instructions.md
Caching patterns for .NET — IDistributedCache, Redis, in-memory, cache-aside, TTL strategies.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).