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/mengrru/spherse/agents-mdgit clone --depth 1 https://github.com/mengrru/SpherseWrote 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/mengrru/spherse/agents-md)<a href="https://agentmods.dev/instructions/mengrru/spherse/agents-md"><img src="https://agentmods.dev/badge/instructions/mengrru/spherse/agents-md.svg" alt="Measured on agentmods" 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 | $0.02912 | $0.02912 |
| Opus 5 | $0.01456 | $0.01456 |
| Sonnet 5 | $0.00582 | $0.00582 |
| Haiku 4.5 | $0.00291 | $0.00291 |
Grade A, and why
Spherse 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 5d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spherse
一个本地运行、开箱即用的个人 Agent 运行时。多个拥有独立系统提示词、工具权限、Skill、MCP 与自动化能力的 Agent 围绕同一用户数据空间工作，并通过 HTML 与 UI SDK 构建可交互、可分发的 Agent Workspace。基于 Electron + React + Fastify，使用 pi-agent-core 作为 Agent 运行时，pi-ai 作为 LLM Provider。
设计文档：docs/official/
待办事项：docs/dev/backlog.md
文档地图
本文是 agent 与新成员的入口：只维护导航、命令和红线，细节一律单一权威来源 + 链接。目录索引见 docs/official/project-structure.md。
Package 一览
| Package | 职责 | 包级守则 |
|---|---|---|
packages/core |
纯 Node.js 核心逻辑（微内核 + Capability） | README |
packages/contracts |
跨进程边界 wire 协议（HTTP/WS schema + parser，server 与 renderer 共同依赖） | README |
packages/presets |
内置模板与预置静态内容 | README |
packages/sdk |
Agent Workspace UI SDK（注入 HTML 卡片的 bridge 脚本与宿主类型） | 遵循 docs/official/ |
packages/i18n |
i18n 基础设施与翻译资源 | README |
packages/server |
Fastify API 层 | README |
packages/app |
共享 React renderer | README（必读） |
packages/desktop |
Electron 桌面壳（main/preload/基础设施） | 遵循 docs/official/ |
packages/web |
Web 版本壳（移动端 PWA） | 遵循 docs/official/ |
packages/landing |
GitHub Pages 项目介绍页 | 遵循 docs/official/ |
读：按需加载
- 全局架构、package 边界、跨包契约 →
docs/official/architecture/index.md，按任务路由查docs/official/README.md - 数据文件格式与存储约定 →
docs/official/data-conventions.md - 测试分层、选型规则、验证链 →
docs/official/testing.md - 术语对齐 / 查一个词指什么 →
docs/official/glossary.md - 目录结构 →
docs/official/project-structure.md - 包内规范 → 对应 package 的 README
- 历史决策与实施记录（容易过时） →
docs/dev/，开发新 feature 时优先参考docs/official/
写：变更 → 必须同步的文档
| 本次变更 | 需同步 |
|---|---|
| 新增/移动/删除文件、目录、package | docs/official/project-structure.md |
| 架构决策、package 边界、capability/装配、API contract 方式 | docs/official/architecture/ 对应域文件（索引见 docs/official/README.md） |
| 数据文件格式、存储位置约定 | docs/official/data-conventions.md |
| 包内编码/review 规范 | 对应 packages/{pkg}/README.md |
| 用户可见文案 | 加载 i18n skill |
| design system、主题机制、聊天 DOM/布局/CSS token | 检查 packages/presets/skills/ 下两个 theme skill |
| feature spec/plan、infra design、bugfix 分析、调研 | docs/dev/{features,infra,bugfix,investigation}/{yyyy-MM-dd-name}/ |
| 完成 backlog 条目 | docs/dev/backlog.md 删除该条，并补充新增条目 |
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.
- 5d ago First seen · 160 lines · 2,912 tokens per session scan A e34ccd284d1f
Spherse AGENTS.md is an instructions file published in the GitHub repository mengrru/Spherse (61 stars, last pushed yesterday), licensed MIT. It adds 2,912 tokens to every session, about $0.0146 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
solo AGENTS.md
AGENTS.md instructions for solo-agent/solo, covering project testing rules and project service lifecycle rules.
research-os AGENTS.md
Instructions for lxinfei5/research-os, covering researchos — constitution, §0 what this is, §1 directory discipline, §2 half-life (innovation 1) — memory design and §3 behavior pillars (innovations 2–5).
Polaris AGENTS.md
AGENTS.md instructions for sponge-b0b/Polaris, covering agents.md, purpose and authority, domain vocabulary, coding conduct and secrets.
AI-System-Design-Consultant CLAUDE.md
Claude Code instructions for deepanshu2711/AI-System-Design-Consultant, covering claude.md, what this is, running it, load-bearing typos — do not "fix" these paths and agent node pattern.
agent-eve CLAUDE.md
Instructions for shehryarsaroya/agent-eve, covering claude.md — agent eve (né the compact, then agent transfer), 0. 🚨 hard rules, 1. what this is, 2. doc map and 3. state of play (2026-07-26).
team-shinchan AGENTS.md
Instructions for seokan-jeong/team-shinchan, covering agents.md - team-shinchan agent map, layer architecture, agent registry, call flow and quick reference.