Synapse AGENTS.md

Project-specific coding rules for Synapse, including how database, application, and device communication layers should be separated. They define naming conventions and responsibilities for repositories, services, presenters, and wire adapters.

In plain words
What is it for?
Use them when changing Synapse's database access, API modules, web components, or device-protocol code.
Why use it?
They reduce accidental mixing of database records, application data, and signed device messages, with some rules checked by guard scripts.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/zai-org/synapse/agents-md
Clone the repo
git clone --depth 1 https://github.com/zai-org/Synapse

Made for: Codex, OpenCode.

Per session 5,342 This file is loaded in full into every session.
When invoked 5,342 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.05342 $0.05342
Opus 5 $0.02671 $0.02671
Sonnet 5 $0.01068 $0.01068
Haiku 4.5 $0.00534 $0.00534

Measured 2d ago against content hash 1ae68460f4f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

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`
AGENTS.md · 172 lines

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_casepackages/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)

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→IsoInstantStringfileId→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

Read the full file on GitHub · 172 lines

Changes

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.

  1. 2d ago First seen · 172 lines · 5,342 tokens per session scan A 1ae68460f4f0

Subscribe to this mod's changes

Synapse AGENTS.md is an instructions file published in the GitHub repository zai-org/Synapse (434 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 5,342 tokens to every session, about $0.0267 per session on Opus 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.

Related

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.

openai/codex · 5,182 tokens

buildNext

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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).

microsoft/vscode · 5,001 tokens

spec-kit 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.

github/spec-kit · 7,040 tokens

langchain 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.

langchain-ai/langchain · 4,345 tokens