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 VidyFoo/antigravity-skill-engine --skill session-managinggit clone --depth 1 https://github.com/VidyFoo/antigravity-skill-engineWrote 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/vidyfoo/antigravity-skill-engine/session-managing)<a href="https://agentmods.dev/skills/vidyfoo/antigravity-skill-engine/session-managing"><img src="https://agentmods.dev/badge/skills/vidyfoo/antigravity-skill-engine/session-managing/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/vidyfoo/antigravity-skill-engine/session-managing"><img src="https://agentmods.dev/badge/skills/vidyfoo/antigravity-skill-engine/session-managing.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 | $0.00031 | $0.01174 |
| Opus 5.5 | $0.00012 | $0.00470 |
| Sonnet 5.5 | $0.00006 | $0.00235 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
session-managing 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 1mo 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Lifecycle Skill
核心理念: 会话生命周期 = 继承 → 工作 → 沉淀 → 闭环升级
自动触发协议
本 Skill 无需手动调用，AI 会在适当时机自动激活。
INHERIT 模式 (继承)
触发时机:
- 新对话开始 (对话历史为空)
- 用户发出首个任务型请求
- 用户明确说 "开始"、"入职"、"onboarding"
执行动作:
1. view_file doc/memory.md (读取 TL;DR 10 条核心认知)
2. view_file .agent/rules/rule-one.md
3. (复杂任务) view_file doc/explanation/architecture.md
4. 静默继承，不打断用户工作流
输出: 无 (静默执行) 或简短确认
DEPOSIT 模式 (沉淀)
触发时机 (满足任一条):
- 产生了新的设计决策或架构选择
- 发现并解决了隐藏的技术问题
- 形成了可复用的编程模式或最佳实践
- 产生了"这个想法太妙了"的闪光洞察
- 对话即将结束且有沉淀价值
执行动作:
1. 提炼本次对话精华 (CORE/PATTERN/DECISION/TIP)
2. view_file doc/memory.md
3. 融合更新 doc/memory.md (去重升维)
4. 如为技术规范 → 写入 doc/specs/
5. 通知用户完成
输出:
## 📦 沉淀完成
**本次新增**:
- `[PATTERN]` {模式名}
- `[DECISION]` {决策名}
✅ memory.md 已更新 (累计 N 条)
手动覆盖
用户可随时说:
- "跳过 onboarding" → 禁用 INHERIT
- "沉淀本次对话" → 强制 DEPOSIT
- "不需要沉淀" → 禁用 DEPOSIT
Doc 系统集成 (Diátaxis)
INHERIT 读取链 (优先级从高到低)
| 层级 | 文件 | 策略 | 说明 |
|---|---|---|---|
| L1 必读 | doc/memory.md (TL;DR) |
始终 | 核心认知与原则 |
| L1 必读 | .agent/rules/rule-one.md |
始终 | 项目宪章与禁忌 |
| L2 按需 | doc/explanation/README.md |
架构与全貌 | 系统索引 |
| L3 上下文 | doc/explanation/subsystems/{xxx}.md |
特定 Feature | 深度理解子系统 |
| L3 上下文 | doc/specs/{xxx}.md |
特定 Feature | 查阅具体规范 |
| L4 入门 | doc/tutorials/quick-start.md |
新手/重置 | 环境搭建与启动 |
DEPOSIT 写入链
根据知识类型选择写入位置：
| 知识类型 (Diátaxis) | 写入目标 | 示例 |
|---|---|---|
| Core Wisdom (智慧/决策) | doc/memory.md |
设计哲学、架构决策、踩坑教训 |
| Understanding (原理/架构) | doc/explanation/subsystems/ |
模块架构图、核心机制解析 |
| Reference (规范/规则) | doc/specs/ |
API 定义、业务规则、边界情况 |
| How-To (指南/测试) | doc/how-to/ |
测试策略、调试指南、操作手册 |
| Archive (历史/草稿) | doc/archive/ |
过时的设计文档、被取代的方案 |
记忆格式规范
类型标签
| 标签 | 含义 |
|---|---|
[CORE] |
核心原则，永恒不变 |
[PATTERN] |
可复用模式 |
[DECISION] |
时间点决策 |
[TIP] |
实用技巧 |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 138 lines · 31 tokens per session scan A 8e6039ab37b1
session-managing is a skill published in the GitHub repository VidyFoo/antigravity-skill-engine (12 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,174 once invoked, about $0.0001 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 skills, from other repositories
mm-handoff
A skill that creates a compact handoff.md summary for starting a new Claude chat when the current chat is full. The file records recent work, current status, open questions, and selected project context.
mm-save-session
An end-of-session recorder for Claude Code that saves the conversation summary and project state in Obsidian notes. Obsidian is a note-taking app that stores information as files.
mm-clear-gate
A read-only checkpoint that uses a script to check whether project notes, handoff files, repository changes, and session records have been saved before clearing context.
mm-setup
A setup guide that personalizes a shared mm system for one user. It asks for details such as your name, work area, tools, language, and Obsidian vault location, then saves them in private configuration files.
mm-vault
A setup tool that creates a private GitHub repository for an Obsidian project memory folder and connects it to Claude.ai project knowledge. Obsidian is a note-taking app that stores information as files.
park
Save current work context for later resumption.