Borrowing it
Nothing to install: this file belongs to wang-baohai/Omni-Stack. 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/wang-baohai/Omni-Stack/main/AGENTS.mdgit clone --depth 1 https://github.com/wang-baohai/Omni-StackWrote 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/wang-baohai/omni-stack/agents-md)<a href="https://agentmods.dev/instructions/wang-baohai/omni-stack/agents-md"><img src="https://agentmods.dev/badge/instructions/wang-baohai/omni-stack/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/wang-baohai/omni-stack/agents-md"><img src="https://agentmods.dev/badge/instructions/wang-baohai/omni-stack/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 | $0.05219 | $0.05219 |
| Opus 5.5 | $0.02088 | $0.02088 |
| Sonnet 5.5 | $0.01044 | $0.01044 |
| Haiku 4.5 | $0.00522 | $0.00522 |
Grade A, and why
Omni-Stack 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 11d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Identity
Omni-Stack is a microservices scaffolding platform built with Spring Boot 4 + Vue 3, organized as a monorepo with a Maven multi-module backend and a standalone npm frontend.
| Layer | Technology | Version |
|---|---|---|
| JDK | OpenJDK | 25 |
| Backend | Spring Boot | 4.0.6 |
| Cloud | Spring Cloud | 2025.1.1 |
| Cloud Alibaba | Spring Cloud Alibaba | 2025.1.0.0 |
| Gateway | Spring Cloud Gateway Server (WebFlux) | 5.0.1 |
| Service Discovery / Config | Nacos Server | v3.1.1 |
| Circuit Breaker / Flow Control | Spring Cloud Alibaba Sentinel client | 2025.1.0.0 (Dashboard optional) |
| Frontend | Vue 3 + TypeScript | 3.5.35 / 5.9.3 |
| Bundler | Vite 8 (Rolldown) | 8.2.1 |
| UI Framework | Element Plus | 2.14.0 |
| State | Pinia | 3.0.4 |
| Router | Vue Router | 5.0.7 |
| Node.js | Node.js LTS | >= 22.12.0 |
System Truth
Architecture, patterns, API contracts, and core flows are documented in docs/. Read those first. This file contains only execution rules and build commands.
| Document | Purpose |
|---|---|
docs/architecture.md |
System boundaries, module map, data flow, RBAC permission system, constraints |
docs/api-contract.md |
Response format, error codes, pagination, naming |
docs/backend-patterns.md |
Java layering, validation, exceptions, logging, security & data permission, OOP rules |
docs/frontend-patterns.md |
Vue/TS patterns, state management, routing, permission control, component conventions |
docs/core-flows.md |
End-to-end traces of login (password + captcha, GitHub social, Gitee social, device code), RBAC functional permission (Flow 5), data permission (Flow 6), XSS defense (Flow 8) |
docs/scheduling.md |
Scheduled task system: dual-track architecture (system tasks + user tasks), XXL-JOB integration, creating new task types |
docs/workflow.md |
Workflow engine: Flowable integration, dual-version model management, multi-instance countersign, candidate resolution, approval flows |
docs/crm.md |
CRM sales pipeline: domain model, 6-layer security, state machine, lead conversion, extension guide |
docs/srm.md |
Current SRM lifecycle, portal Saga, evaluation/risk, data scope and API contracts |
docs/design/srm-design.md |
SRM design decisions, reviewed implementation snapshot and history |
docs/design/procurement-design.md |
Procurement: material catalog, requisition approval, RFQ/quotation, purchase order and goods receipt boundaries |
docs/design/asset-design.md |
Asset MVP: asset ledger, procurement receipt ingestion, allocation/return, transfer/disposal approval and data scope |
docs/mq-reliability.md |
Reliable message sending: Transactional Outbox pattern, status machine, retry strategy, tenant isolation, new service onboarding |
docs/observability.md |
Metrics, W3C tracing, structured logs, local observability stack, dashboards, alerts and SLO template |
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.
- 11d ago Changed · -201 lines · -4,660 tokens per session 885c3574e4ff
- 21d ago Changed · -33 lines · +268 tokens per session d51242b0fd88
- 2mo ago First seen · 506 lines · 9,611 tokens per session scan A f8adf53411be
Omni-Stack AGENTS.md is an instructions file published in the GitHub repository wang-baohai/Omni-Stack (90 stars, last pushed 11d ago), licensed Apache-2.0. It adds 5,219 tokens to every session, about $0.0209 per session on Opus 5.5. 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 2026-08-30.
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).
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).
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.