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 skills add mengrru/Spherse --skill spherse-guidegit 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/skills/mengrru/spherse/spherse-guide)<a href="https://agentmods.dev/skills/mengrru/spherse/spherse-guide"><img src="https://agentmods.dev/badge/skills/mengrru/spherse/spherse-guide/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/skills/mengrru/spherse/spherse-guide"><img src="https://agentmods.dev/badge/skills/mengrru/spherse/spherse-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.03386 |
| Opus 5 | $0.00032 | $0.01693 |
| Sonnet 5 | $0.00013 | $0.00677 |
| Haiku 4.5 | $0.00006 | $0.00339 |
Grade A, and why
spherse-guide 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 10d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spherse 使用指南
Spherse 是一个本地运行、开箱即用的个人 Agent 运行时。一个普通文件夹就是一个项目,多个拥有独立提示词、工具、Skill、MCP、自动化和会话的 Agent 围绕同一份用户文件协作。Agent 还可以生成 HTML 页面,并通过 UI SDK 把文件、会话和数据能力组合成可交互的 Workspace。
核心概念
项目
项目就是用户磁盘上的普通文件夹:
project-root/
├── AGENTS.md
├── CHANGELOG.md
├── 用户文件...
└── .spherse/
├── project.yaml
├── theme.css
├── skills/
└── agents/
- 普通文件是项目主体,可继续使用外部编辑器和版本控制管理。
AGENTS.md是所有 Agent 共享的项目指令。CHANGELOG.md可由启用了append_changelog的 Agent 追加记录。.spherse保存项目 ID、Agent、会话、主题、Skill、MCP、触发器等平台元数据。- 桌面端可以同时打开多个项目,并从左侧项目头像切换。
Agent
每个 Agent 都有独立的:
- 名称、别名和 system prompt
- 启用的工具
- 预加载上下文文件
- 会话历史
- 聊天主题
- MCP 连接器
- 触发器
- 私有 Skill 和记忆数据
Agent 创建界面可配置 Prompt、工具、上下文文件、时间感知、聊天主题和 YOLO 模式。工具必须显式启用;未启用的工具不会交给模型。
新建项目会自带一个预设 Agent「小助手」:通用型助手,默认开启除 run_command 外的全部工具,可随时在界面中修改或删除。
会话
同一个 Agent 可以拥有多个互相独立的会话。用户可以:
- 新建、打开、重命名、删除和导出会话
- 查看流式回复、工具调用、文件 diff、命令输出和 token 使用
- 中止正在生成的回复或重试失败的回复
- 回答 Agent 的问题,批准或拒绝危险操作
- 在桌面端将一个会话浮动为可拖拽窗口
- 在文档中划选文字,附带来源发送给现有会话或新 Agent
切换页面不会终止后台运行。一个会话同一时间只能执行一个 turn;忙碌时不会排队第二条消息。
功能地图
项目文件与内容浏览
桌面端 Files 区域支持浏览、新建、编辑、保存、删除文件和目录,也可以复制项目相对路径或将文件打开为多个浮窗。
Content Browser 支持:
- Markdown 与 YAML frontmatter
- HTML 预览和源码切换
- 图片预览
- 普通文本编辑与搜索
- 外部文件变化自动刷新
- 二进制文件交给系统默认应用打开
用户可在 Files 区域配置“AI 读取限制”,禁止 Agent 读取和写入指定项目路径。该策略不限制 run_command 启动的子进程。
项目欢迎页
项目根路由可以展示一个自定义 HTML 页面或图片(html、png、webp、svg 等常见格式),适合作为项目首页、导航入口、仪表盘或世界观导览。
配置方式:左侧活动栏右键当前项目头像 →「设置 → 欢迎页」→ 填写项目内相对路径,或者由启用了 manage_project_config 工具的 Agent 在对话中设置(路径会经过校验)。清空配置可恢复默认;未显式配置时自动尝试项目根目录的 index.html。欢迎页文件或 project.yaml 配置被修改后会自动刷新;文件缺失或加载失败时回退到默认空状态。
工具与审批
常见工具类别:
| 目的 | 工具 |
|---|---|
| 文件读取 | read_file、list_files、search_content |
| 文件修改 | write_file、edit_file、move_file、copy_file |
| 结构化数据 | read_data、query_data、mutate_data |
| 交互与展示 | ask_user、render_card、generate_image |
| 项目协作 | append_changelog、load_skill、emit_trigger_event |
| 记忆 | memory_save、memory_recall |
| 高级操作 | run_command、manage_agent、manage_trigger、manage_project_config(Agent 配置界面中三个 manage_* 合并为单一「管理项目」选项,勾选即同时启用) |
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.
- 10d ago First seen · 266 lines · 65 tokens per session scan A e56c30249983
spherse-guide is a skill published in the GitHub repository mengrru/Spherse (71 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 3,386 once invoked, about $0.0003 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 skills, from other repositories
llmlint
A Chinese-prose rule library with two entry points. Before writing, emit the rules as writing constraints to load into a system prompt or style guide. After writing, lint the draft with static rule hits, neural AIGC heatmaps, contextual review, approved repair, and local learning notes. Use when drafting or rewriting…
profile-system-guide
Guide users and agents through Neuro Book harness, TSX profiles, ProfileTurnPlan, skills, user-assets overlays, settings forms, profile home resources, profile compile checks, templates, system restore, and safe profile editing.
novel-technique-character-card-workshop
A workshop for turning rough character ideas into detailed, usable character profiles. It supports structured question cycles, personality layers, visual themes, and checks against reducing a character to a few labels.
novel-writer-execution
An internal execution guide for a writer profile after it receives a brief. It describes the detailed workflow, decision points, and common mistakes.
RP模式
A set of instructions for running a role-playing session under the NeuroBook RP protocol. RP means role-play, where characters and events are simulated according to defined rules.
skill-creator-zh
A skill for creating and maintaining skills in the Neuro Book repository. Skills are reusable instruction packages that guide an agent through a particular kind of work.