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/stepfun-ai/step-realtime-cli/agents-mdgit clone --depth 1 https://github.com/stepfun-ai/Step-Realtime-CLIWhat 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 | $0.03516 | $0.03516 |
| Opus 5 | $0.01758 | $0.01758 |
| Sonnet 5 | $0.00703 | $0.00703 |
| Haiku 4.5 | $0.00352 | $0.00352 |
Grade A, and why
Step-Realtime-CLI 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 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.
How it starts
The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Step Realtime CLI 项目架构与开发原则。
1. 总体分层
Step Realtime CLI 采用分层 monorepo 架构，默认依赖方向如下：
packages/protocol <- packages/utils <- packages/core <- packages/agent-sdk <- packages/realtime <- src/gateway <- packages/sdk <- clients
旁路依赖如下：
src/bootstrap -> packages/coresrc/commands -> src/runtime -> src/gatewayskills/* -> packages/coreextensions/* -> packages/core或src/gatewaysrc/bootstrap承载多个入口复用的启动 / 配置 / prompt 辅助逻辑
这里的 clients 指：
src/cli/src/tui/ui/apps/desktop/apps/*中未来新增的独立端侧应用
基础规则：
- 上层可以依赖下层，下层不得反向依赖上层。
packages/core不依赖具体厂商 SDK、数据库、WebSocket 服务端或 UI 层。src/gateway是应用组装层，不是公共库层。packages/sdk依赖的是 gateway 的协议，不是 gateway 的源码实现。- UI、TUI、CLI、Desktop 默认只依赖
packages/sdk，不直接依赖src/gateway。
2. 各层职责
packages/protocol/
负责跨边界契约：
- request/response schema
- event schema
- DTO
- session、workspace、agent、model 的共享类型
该层应尽量保持纯类型和纯协议，不放业务实现。
packages/core/
负责核心运行时与领域语义：
- Agent Loop
- Agent / SubAgent / AgentTeam 编排
- session / workspace 领域模型
- context / prompt 组装
- memory 抽象
- tool / skill / provider / model 抽象接口
该层默认依赖 packages/protocol，并允许依赖 packages/utils 这类无领域语义的基础共享层；不得直接依赖具体外部实现。
packages/agent-sdk/
负责对外暴露的 Agent 构建 SDK：
- 基于
packages/core暴露稳定的 Agent / Tool / Skill 构建 API - 供第三方或上层应用以编程方式声明 agent / 工具
- 仅依赖
packages/core、packages/protocol、packages/utils
该层不得反向依赖 packages/sdk、src/*、apps/*、extensions/*、skills/*、ui/（由 .dependency-cruiser.cjs 的 agent-sdk-no-implementation-deps 强制）。
packages/realtime/
负责实时音频 / 语音相关的协议与运行时：
- 实时音频 stream 抽象
- VAD / AEC / 语音通道的协议层与共享类型
- 供 gateway 与
extensions/realtime-*复用的实时运行时基础设施
该层不放具体厂商适配；具体实现走 extensions/realtime-*。
packages/utils/
负责基础共享工具与纯辅助函数：
- 文本、路径、错误、token 估算等无业务状态工具
- 纯格式化、解析、归一化函数
- 可被 core / gateway / sdk / src/bootstrap / skills / extensions 复用的轻量 helper
该层不拥有 session authority，不实现 agent loop，不放具体外部系统集成。
skills/
负责 agent-facing 能力单元：
skills/builtin/：内置工具
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 · 356 lines · 3,516 tokens per session scan A 43929e85a9f4
Step-Realtime-CLI AGENTS.md is an instructions file published in the GitHub repository stepfun-ai/Step-Realtime-CLI (45 stars, last pushed 11d ago), licensed MIT. It adds 3,516 tokens to every session, about $0.0176 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 2026-08-30.
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
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, 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.
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.