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/oneworks-ai/app/agents-mdgit clone --depth 1 https://github.com/oneworks-ai/appWhat 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 | $0.06793 | $0.06793 |
| Opus 5 | $0.03397 | $0.03397 |
| Sonnet 5 | $0.01359 | $0.01359 |
| Haiku 4.5 | $0.00679 | $0.00679 |
Grade A, and why
app 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.
命令退出 0 且 JSON 中对应服务为 `ready: true` 时，按 target 做最短交付并停止，不要再做 `ps`、`curl` 或读日志等二次验证： How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Agent Guide
最高优先级：开发服务 Fast Path
本节优先级高于本文所有后续阅读、规则加载和 worktree 初始化判断。
如果用户意图是“取最新代码并启动 web 服务”“拉取最新代码并启动一个 web 服务”“启动 web 服务”“start web dev server”，唯一动作是在仓库根目录直接执行：
pnpm --silent tools dev-service ensure web --json
此类请求不要做额外预检查或成功后二次验证；dev-service ensure 已经负责 fetch、安全拉取 / 对齐、workspace install 校验、端口避让、后台进程、操作租约、状态写入和探活。相关经验和反例见 .oo/rules/maintenance/common-issues.md 的 “Subagent 启动 Web 服务超过 1 分钟”。
命令退出 0 且 JSON 中对应服务为 ready: true 时，按 target 做最短交付并停止，不要再做 ps、curl 或读日志等二次验证：
- Web / PWA / homepage / docs 等前端页面服务：用 Browser / browser-use 自动打开状态里的
clientUrl/docsUrl，然后只回复一个可点击前端入口链接；不要在成功消息里展开其他 URL、PID 或日志路径，除非用户明确需要排查信息。 - Electron / desktop / launcher：直接打开输出对应的开发态应用窗口；成功消息保持简短，不要让用户再手动打开应用。
- 只有命令失败时才读取同一 target 的有限
events和已脱敏logs并继续排查。
其他开发服务启动意图同样直接走统一 Commander CLI：
用户要求拉取最新代码并启动开发服务时，不要手动推理端口、依赖安装、后台进程或多 worktree 进程；在仓库根目录直接执行统一 Commander CLI：
pnpm --silent tools dev-service ensure <target> --json
意图识别表：
- 普通 Web UI / “启动一个 web 服务” / “拉取最新代码，并启动一个 web 服务”：
pnpm --silent tools dev-service ensure web --json - Electron / 桌面端 / launcher：
pnpm --silent tools dev-service ensure electron --json - Electron 且要打开当前仓库作为 workspace：
pnpm --silent tools dev-service ensure electron-workspace --json - PWA / 独立前端 / standalone client：
pnpm --silent tools dev-service ensure pwa --json - 官网首页预览 / homepage preview：
pnpm --silent tools dev-service ensure homepage --json - 使用文档 / docs 本地预览：
pnpm --silent tools dev-service ensure docs --json - 独立 management daemon：
pnpm --silent tools dev-service ensure daemon --json - Relay Server + Relay Admin：
pnpm --silent tools dev-service ensure relay --json - Electron agent control bridge：
pnpm --silent tools dev-service ensure desktop-control --json - Android 可见模拟器：
pnpm --silent tools dev-service ensure android-emulator --json
pnpm tools 通过 scripts/run-tools.mjs 注册 TS；如果新 worktree 缺少 register 依赖，会先执行 pnpm install。dev-service ensure 会安全执行 git fetch --prune origin，在工作区干净时按当前状态拉取 / 对齐最新代码，按需校验 workspace 安装，后台启动对应开发服务，自动避开已占用端口，并在探活成功后输出机器可读状态。如果当前 worktree 已有同 target 服务且探活成功，会直接复用并返回 URL。
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 · 177 lines · 6,793 tokens per session scan A 69c5bdcb3703
app AGENTS.md is an instructions file published in the GitHub repository oneworks-ai/app (18 stars, last pushed 2d ago), licensed MIT. It adds 6,793 tokens to every session, about $0.0340 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.
Other instructions, from other repositories
AionUi AGENTS.md
Instructions for iOfficeAI/AionUi, covering aionui - project guide, code conventions, file & directory structure, naming and ui library & icons.
spec-kitty AGENTS.md
Instructions for Priivacy-ai/spec-kitty, covering spec kitty development guidelines, ⚠️ critical: load the project charter first, ⚠️ critical: template source location, ⚠️ critical: use canonical sources, never improvise and ⚠️ critical: git workflow — no direct pushes to origin/main.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).
gemini-cli-desktop AGENTS.md
Instructions for Piebald-AI/gemini-cli-desktop, a project described as: Web/desktop UI for Gemini CLI/Qwen Code. Manage projects, switch between tools, search across past conversations, and manage MCP servers, all from one multilingual interface, locally or remotely.
sessionview AGENTS.md
Instructions for tyql688/sessionview, covering sessionview, commands, app / frontend, gates must pass under both feature sets: default (gui) and and --no-default-features --features headless.
SubFrame AGENTS.md
Instructions for Codename-11/SubFrame, covering subframe - subframe project, core working principle, relationship to native ai tools, session start and concurrent work & worktrees.