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/zhinjs/zhin/summarizenpx skills add zhinjs/zhin --skill summarizegit clone --depth 1 https://github.com/zhinjs/zhinWrote 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/zhinjs/zhin/summarize)<a href="https://agentmods.dev/skills/zhinjs/zhin/summarize"><img src="https://agentmods.dev/badge/skills/zhinjs/zhin/summarize.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 | $0.00061 | $0.01486 |
| Opus 5 | $0.00030 | $0.00743 |
| Sonnet 5 | $0.00012 | $0.00297 |
| Haiku 4.5 | $0.00006 | $0.00149 |
Grade A, and why
summarize scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 服务可达性：… — 来源：curl/日志 How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summarize
把已有材料压缩成可交接、可执行的摘要。只写能指回证据的事实；无证据不写结论。
何时使用
- 长对话 / 调试会话交接
- CI / 测试失败浓缩
- 写入 Issue、PR、MEMORY 前的草稿
不适用
- 用户要「分析根因并给出修复方案」→ 先调查再总结，或直接用开发 skill
- 材料只有一句模糊描述 → 先追问，不要编造细节
工作流
第 1 步：确认受众与材料是否够用
| 用途 | 长度 | 必含 |
|---|---|---|
| 口头交接 | 5–10 行 | 现状、阻塞、下一步 |
| Issue/PR 摘要 | 中等 | 决策、验证命令、风险 |
| 持久记忆 | 短条目 | 稳定事实、配置约定、踩坑 |
材料充分度检查（缺任一项则进入「材料不足模式」，见第 2 步）：
- 失败现象或目标（用户原话或日志一行）
- 至少一条已执行的命令 + 结果（或明确写「未跑验证」）
- 相关路径 / 版本 / 配置名（如有）
第 2 步：选模式
A. 材料不足模式（无日志、无命令结果、仅口头描述）：
禁止输出「已完成」章节。只用：
## 概要
材料不足，以下为**待确认清单**（非最终结论）
## 已从上下文提取（附来源）
- [待确认] … — 来源：用户原话 / 对话片段
## 待用户补充
- [ ] 完整错误日志或 CI job 链接
- [ ] 已运行的命令及输出
- [ ] 相关文件路径（如 `zhin.config.yml`）
## 建议下一步
1. …
B. 材料充足模式：按第 3–4 步选模板，并遵守事实分级。
第 3 步：事实分级（写入时强制）
| 标记 | 含义 | 可放入 |
|---|---|---|
[确认] |
有命令输出、文件内容、可复现日志 | 已完成 |
[待确认] |
仅对话提及，未验证 | 未完成 / 阻塞 或独立「待确认」节 |
| 禁止 | 无来源的推断、脑补因果 | 任何章节 |
每条 bullet 格式：[确认] 结论 — 来源：pnpm test` 失败于 demo-config.test.ts ENOENT``
第 4 步：按场景输出
默认（材料充足）：
## 概要
（1–2 句，仅 [确认] 事实）
## 已完成
- [确认] … — 来源：…
## 未完成 / 阻塞
- [待确认] … — 来源：…
## 关键命令与结果
- `命令` → 结果（一行）
## 下一步（按优先级）
1. …
CI / 测试失败（含 ENOENT、类型错误、端口占用）：
## 概要
Job/包：… | 首条错误：…
## 失败信号
- 命令：…
- 错误（原文一行）：…
- 涉及文件：…（若 ENOENT 写明缺失路径）
## 已排除（须 [确认]）
- … — 来源：…
## 下一步
1. …
调试会话交接：
## 当前状态
- 分支/commit：…
- 服务可达性：… — 来源：curl/日志
## 时间线（按发生顺序，每条带标记）
1. [确认] … — 来源：…
## 已尝试
- `命令` → 结果
## 阻塞
- [待确认] … — 来源：…
## 待办
1. …
用户要求 exhaustive 时再扩展章节；默认保持短。
🔴 CHECKPOINT · 敏感信息
写入 Issue、PR、公开 MEMORY 前：删除 token、.env、用户 ID、内网 URL → <REDACTED>。
🔴 CHECKPOINT · 材料不足
若第 1 步检查未通过，必须用材料不足模式，不得用默认模板的「已完成」填空。
失败与兜底
| 触发条件 | 一线处理 | 仍失败 |
|---|---|---|
| 上下文过长 | 按主题分段摘要再合并；保留来源标记 | 请用户指定时间范围或文件 |
| 材料矛盾 | 并列两种说法，均标 [待确认] |
不合并成单一「真相」 |
| 用户只要一句话 | 仍给 5 行结构：概要 + 阻塞 + 下一步 | 不省略失败原因 |
不要做什么
- 不要把推测写进「已完成」（无命令/日志支撑 =
[待确认]） - 不要把摘要写成营销或过度乐观
- 不要省略失败原因（禁止只写「有问题」「500」）
- 不要无日志时编造调试时间线
- 不要在摘要里泄露 token、密码、私聊 ID
- 不要默认生成长报告（除非用户明确要求）
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.
- 4d ago First seen · 177 lines · 61 tokens per session scan A 429600740424
summarize is a skill published in the GitHub repository zhinjs/zhin (135 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 1,486 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Apple Notes
Open Notes.app and create or update iCloud notes on macOS using memo when possible and AppleScript when direct app automation is more reliable.
Release Notes Generator
Generate professional software release notes from a commit log: classify changes, write user-facing summaries, draft a publishable announcement, and assess release readiness. Use for release, changelog, version, and deploy requests.
GIF Search
Search and download reaction GIFs through the Tenor API using curl and jq when the user wants lightweight media retrieval.
knowledge-absorber
深度解析链接/文档/代码，生成导师级教学笔记 + Wan 2.7 知识海报。 Use when user asks to: 学习、分析、解读、整理、吸收、读懂 任何文档或代码 Trigger keywords: 学习、分析、知识卡片、知识海报、解读文档、整理笔记、知识库、存入知识库 支持 PDF/Word/Markdown/代码/图片，自动真理锚定验证，国学内容自动水墨风格。 When user provides: URL链接、文件路径、代码文件、图片 → 生成知识卡片 When user says: "生成海报"、"知识海报" → 额外生成 Wan 2.7 信息图.
task-handoff
DeepSeek-friendly long-task project memory and cross-session handoff. Use when the user says handoff, 交接, 续上, 接着做, 项目记忆, long task, resume session, save progress, 跨会话, or when starting a multi-hour / multi-day coding task that must survive chat resets. Provides init/save/ recall/status workflows and compact context…
apple-notes
Interact with the Apple Notes app. CRUD operations for persistent storage of thoughts, data, and information across sessions.