TypingMindTypingMindThe best frontend for AI
Agent Phase Closeout logo

Agent Phase Closeout

OrganizationPopular
hashgraph-online
agent-phase-closeout

中文阶段收尾技能。用于完成一个阶段、准备开新对话、需要更新状态快照、冻结模块、整理已完成任务和下一步任务时。触发语包括"阶段收尾""帮我收工""准备开新对话""更新快照""冻结阶段""总结当前状态"。

Overview

Publisherhashgraph-online
Repositoryawesome-codex-plugins
Skill nameagent-phase-closeout
Stars
1.3K
Forks
360
Bundled files
3
LicenseApache-2.0
Links
Skill sourceRepositoryHomepage
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by hashgraph-online on GitHub. Read the source before you install it.

Installation

Install the Agent Phase Closeout AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/1139030773-cmd/agent-workflow-system/skills/agent-phase-closeout
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git /tmp/awesome-codex-plugins
mkdir -p .claude/skills
cp -r /tmp/awesome-codex-plugins/plugins/1139030773-cmd/agent-workflow-system/skills/agent-phase-closeout .claude/skills/agent-phase-closeout
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Agent Phase Closeout in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Agent Phase Closeout on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Agent Phase Closeout is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Codex 阶段收尾

身份：收尾者。总结、冻结、更新快照。绝对禁止开发新功能或引入新方案。

遵守统一行为规范（职能隔离 / 动作校验 / 状态机 / 五级纠错 / 回滚 / 证据链）。

📍 阶段位置

[●入口] → [●引导] → [●策划] → [●执行] → [●审计] → [◉收尾]
 当前角色: 收尾者 | 上一站: 审计 | 下一站: 结束/新循环

当前阶段自动写入 STATE_SNAPSHOT.md 的 current_phase 字段。

硬边界

允许禁止
总结已完成内容开发新功能
汇总证据链到 DECISIONS.md引入新方案
冻结模块和接口修改代码
生成新对话启动口令隐藏未验证内容
标记未完成任务跳过轻量审计
写入 .resume/ session 文件只写 RESUME.md 不写 .resume/

Session 文件写入

收尾时必须写两个位置（顺序：先 .resume/，后 RESUME.md）：

  1. .resume/session-YYYYMMDD-HHmmss.md（主）— 当前窗口专属 checkpoint
    • session ID 用收尾时刻的时间戳生成
    • 文件格式：与 RESUME.md 相同的 5 字段结构，额外包含 session_id
  2. 根目录 RESUME.md（副）— 向后兼容 fallback，只保留最新一条任务信息

同一任务多次收尾用不同 session ID → 自然产生多个文件 → "继续"时按 task_name 去重，只展示最新。 |

优先读取

真相源文件：PROJECT.md、TASK_QUEUE.md、DECISIONS.md、STATE_SNAPSHOT.md

工作流程

0. 区分收尾类型（最先执行）

必须问用户这一句，不跳过：

这一阶段完成了。下次还要继续吗？

"继续" → 阶段收尾（保留活跃，下次"继续"能找到） "不做了" / "归档" → 归档项目（打包到 archive/）

用户选"阶段收尾"→ 走下面 1-7 步 + 写 .resume/ session 文件。 用户选"归档"→ 跳到归档项目模式。

1. 收尾前快速审计

  • 有未记录决策？→ 先补充
  • 有未完成功能？→ 标记，不隐藏
  • 有偏离？→ 先调用 agent-drift-auditor

2. 总结完成内容 + 验证结果

3. 列出未完成（待开始 / 进行中 / 阻塞）

4. 识别新增决策 → 写入 DECISIONS.md

5. 冻结判断（接口 / 模块 / 命名）

6. 更新真相源

  • STATE_SNAPSHOT.md：对照旧版本逐字段确认后再改，禁止凭空重写。特别是 active_tasks 列表——旧版本有的条目不能丢，只能增/改状态/删已完成。
  • TASK_QUEUE.md：移动已完成 → 设新任务
  • DECISIONS.md：汇总证据链 + 新增决策
  • PROJECT.md：更新目标、阶段、冻结区域

7. 生成新对话启动口令

text
这是新对话。请先读取 PROJECT.md、DECISIONS.md、TASK_QUEUE.md 和 STATE_SNAPSHOT.md。
以这些文件为准，总结当前状态，并告诉我下一步唯一行动。

证据链汇总

本轮所有动作记录 → 写入 DECISIONS.md 附录。

偏离处理

收尾中发现新问题 → 不自己修 → 调 agent-drift-auditor。

交互预算自检

收尾输出前检查：

  • 总结信息量是否可控（≤1 屏）？
  • 未完成任务清单是否清晰可逐个确认？
  • 新对话启动口令是否精简？

禁止事项

  • 不开发新功能 / 不隐藏未验证内容
  • 不把聊天历史当唯一状态来源
  • 不跳过收尾前审计

📦 归档项目模式

用户说"归档项目""归档当前项目""这个项目做完了，帮我归档"时触发。

归档流程（自动执行）

步骤操作
1从 RESUME.md 提取 project name + 当前阶段
2创建 archive/{project-name}-{date}/ 目录
3复制 TASK_QUEUE.md → 归档目录（记录任务历史）
4复制 RESUME.md → 归档目录（记录最终状态）
5复制活跃 .resume/ session 文件 → 归档目录
6复制 PROJECT.md → 归档目录（项目总览 = 归档总结，无需重新生成）
7更新 archive/INDEX.md 加一行：项目名 / 归档日期 / 状态
8问用户："当前活跃文件要清理吗？"（不自动删）

归档后 INDEX.md 更新

| 股票分析网站 | 2026-06-11 | ✅ 完成 | 12 tasks |

禁止事项

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Agent Phase Closeout AI skill do?

中文阶段收尾技能。用于完成一个阶段、准备开新对话、需要更新状态快照、冻结模块、整理已完成任务和下一步任务时。触发语包括"阶段收尾""帮我收工""准备开新对话""更新快照""冻结阶段""总结当前状态"。

Why use Agent Phase Closeout on TypingMind?

Because you install it once and use it with any model. Agent Phase Closeout is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Agent Phase Closeout in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/1139030773-cmd/agent-workflow-system/skills/agent-phase-closeout. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Agent Phase Closeout?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Agent Phase Closeout?

As many as you like. As long as a model supports skills, you can use Agent Phase Closeout with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Agent Phase Closeout AI skill free?

Yes. It is published on GitHub by hashgraph-online under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
obra logo

Subagent Driven Development

obra
CommunityPopular

Use when executing implementation plans with independent tasks in the current session

25.8K
288.1K
6 files
View
affaan-m logo

Unified Memory

affaan-m
CommunityPopular

Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer…

40.4K
270.2K
1 files
View
NousResearch logo

Draw Your Font

NousResearch
OrganizationPopular

Turn a handwriting photo into an installable TTF font.

53.5K
250.4K
1 files
View
NousResearch logo

Adversarial Ux Test

NousResearch
OrganizationPopular

Roleplay a hostile user to find and triage UX pain points.

53.5K
250.4K
Instructions
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇