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 skills/hashgraph-online/awesome-codex-plugins/agent-phase-closeoutnpx skills add hashgraph-online/awesome-codex-plugins --skill agent-phase-closeoutgit clone --depth 1 https://github.com/hashgraph-online/awesome-codex-pluginsWrote 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/hashgraph-online/awesome-codex-plugins/agent-phase-closeout)<a href="https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/agent-phase-closeout"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/agent-phase-closeout.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 | $0.00073 | $0.01416 |
| Opus 5 | $0.00036 | $0.00708 |
| Sonnet 5 | $0.00015 | $0.00283 |
| Haiku 4.5 | $0.00007 | $0.00142 |
Grade A, and why
agent-phase-closeout 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- agent-phase-closeout — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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）：
.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
- 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
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） |
What ships with it
4 files 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.
- 5d ago First seen · 131 lines · 73 tokens per session scan A e0b0847e1b71
agent-phase-closeout is a skill published in the GitHub repository hashgraph-online/awesome-codex-plugins (859 stars, last pushed 6d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,416 once invoked, about $0.0004 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
search
Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.
jira-cli
Interact with Jira from the command line to create, list, view, edit, and transition issues, manage sprints and epics, and perform common Jira workflows. Use when the user asks about Jira tasks, tickets, issues, sprints, or needs to manage project work items.
project-dashboard-builder
Generates a self-contained single-file HTML project dashboard (status banner, milestones, risks heat list, decisions log, links) from the tracker files in /Documents/Cowork/projects/, saved as dashboard- -YYYY-MM-DD.html. Use when the user asks for a project dashboard, a shareable or pinnable status page, an HTML…
project-status-tracker
Maintains living project files (project.md, decisions.md, risks.md, links.md) in a per-project OneDrive folder from emails, Teams channels and meeting transcripts, and generates a weekly DRAFT status document in Word. Use when the user asks to set up tracking for a project, update a project's status files, log a…
transcript-to-actions
Turns a meeting transcript into a structured action-items file, To Do or Planner tasks where writes can be confirmed, and one DRAFT follow-up email per action owner. Use when the user shares, names, or points to a meeting transcript or recap and asks for action items, decisions, follow-up tasks, or post-meeting owner…
administrative-manager
Expert administrative manager with 10+ years experience in office management, facilities coordination, vendor management, and administrative operations. Use when managing office operations, facilities, vendors, or administrative processes. Use when: working with administrative-manager.