workbuddy-context-handoff SKILL.md skillA

workbuddy-context-handoff from renky1025/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add renky1025/agent-skills/workbuddy-context-handoff@git:20260925.32ce6c0

Pins git:20260925.32ce6c0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
renky1025/agent-skills
Path
workbuddy-context-handoff/SKILL.md
Versions recorded
2
Latest version
git:20260925.32ce6c0, committed Sep 25, 2026
First version recorded
Sep 16, 2026
Size
7,623 bytes
Repository stars
11
License
MIT

给 WorkBuddy(桌面端 CodeBuddy Code 运行时)配置基于 hooks 的上下文 handoff 门禁 —— 上下文占用达阈值时自动强制产出 handoff 文档,新会话自动注入继续干活。也用于排查 WorkBuddy hooks / 上下文压缩阈值 / transcript 用量相关问题。触发场景:上下文到 N% 自动生成 handoff、交接文档、新会话续接、hooks 怎么配、为什么自动压缩了、上下文用量怎么算、context handoff、auto compact。注意:本技能的平台路径与 hook 事件名是 WorkBuddy 专有,不适用于其它 agent 运行时。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# WorkBuddy 上下文 handoff 门禁

## Purpose

在 WorkBuddy 桌面端搭一条"上下文快满 -> 强制产出 handoff 文档 -> 新会话自动续接"的流水线。

- **触发端**:Stop hook,按 transcript 里的 token 用量判断是否到阈值,到了就用
  `{"continue": false, "reason": "..."}` 强制模型先写 handoff。
- **注入端**:SessionStart hook,把本项目最新未被消费的 handoff 注入新会话上下文。
- 附带用途:解释/排查 WorkBuddy 的自动压缩阈值、hooks 事件与 transcript 用量计算。

## When to Use

- 用户要"上下文到 N% 自动生成 handoff / 交接文档 / 新会话续接"。
- 用户问 WorkBuddy hooks 怎么配、为什么自动压缩了、上下文用量怎么算。
- 需要定位 WorkBuddy 桌面端的运行时行为(阈值、config option、hook 事件)。
- 触发词:上下文交接、handoff、上下文压缩、自动压缩、hooks 配置、新会话续接、
  context handoff、auto compact。

## When NOT to Use

- 用户只是想知道"我现在用了多少上下文" -> 直接按 transcript 算一次回答,不必配 hook。
- 目标运行时不是 WorkBuddy 桌面端(路径、事件名、环境变量都不同)-> 不适用,先确认运行时。
- 用户要的是一份手工交接文档 -> 直接写,不需要这套门禁。

## Workflow

1. **确认位置与备份**:定位 settings(用户级 `~/.workbuddy/settings.json` 或项目级
   `<proj>/.workbuddy/settings.json`),先备份,再读现有 `hooks` 键。
2. **写三个脚本**到 `~/.workbuddy/hooks/`:`handoff-trigger.mjs`(Stop)、
   `handoff-resume.mjs`(SessionStart)、`run-hook.sh`。各文件职责与防死循环要求见
   `references/hook-implementation.md`。
3. **注册 hooks**(合并进 settings 的 `hooks` 键,不要整体覆盖):

```json
"hooks": {
  "Stop": [
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add renky1025/agent-skills/workbuddy-context-handoff@sha256:c3dc386450eff90f

The line at the top of this page pins the label git:20260925.32ce6c0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_bsnwxkkxkzj62qid.svg)](https://markdownregistry.com/a/art_bsnwxkkxkzj62qid)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Sep 16, 2026 and Sep 25, 2026, about one every 9 days.

versioncommittedcommitsizeaudit
git:20260925.32ce6c0 latest2026-09-25 32ce6c0 7,623 BA view · diff
git:20260916.b57377e2026-09-16 b57377e 5,108 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7623 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

renky1025/agent-skills · 11 stars · license MIT · pushed 2026-10-10 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_bsnwxkkxkzj62qid
GET https://markdownregistry.com/api/v1/resolve?ref=renky1025/agent-skills/workbuddy-context-handoff
GET https://markdownregistry.com/api/v1/blob/c3dc386450eff90f13eef05edc7fad8d2b1868b6ec0b0e97940d976748436797

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from renky1025/agent-skills

AGENTS.md AGENTS.md file
renky1025/agent-skills · AGENTS.md
git:20260925.32ce6c0 · audit A · 11 stars
agent-coding-style SKILL.md skill
renky1025/agent-skills · agent-coding-style/SKILL.md · Coding agent 必须遵守的确定性回答与操作规则,完全取自 Codex gpt-5.2 模型指令模板 (gpt-5.2-codex_instructions_template.md)。覆盖:回复格式、工作呈现、搜索、编辑与…
git:20260925.32ce6c0 · audit A · 11 stars
article-deconstructor SKILL.md skill
renky1025/agent-skills · article-deconstructor/SKILL.md · 拆解高流量文章:输入一篇文章,产出结构化拆解报告——核心观点与副观点、说服策略矩阵、情绪触发地图、金句库、情感曲线、情感层次、论证多样性、视角转化、语言风格,以及可复用的句式模板与写作模板。触发场景:用户要分析文章结构、提取写作技巧、学习高…
git:20260925.32ce6c0 · audit A · 11 stars
black-humor-writing SKILL.md skill
renky1025/agent-skills · black-humor-writing/SKILL.md · 生成有传播力的黑色幽默/讽刺/搞笑内容(推文、段子、评论文案、文章段落)。基于单立人单口喜剧教材,用五步 SOP 把生活观察变成预期违背式的笑点:定主题+态度+前提 -> 构建预期违背 -> 夸张荒谬点 -> 制造情绪冲突 ->…
v1.0.0 · audit A · 11 stars
chatgpt-bridge SKILL.md skill
renky1025/agent-skills · chatgpt-bridge/SKILL.md · 用用户本机已登录的 chatgpt.com 会话做两件事:(1) 新建对话,把你不确定/不清楚的技术问题发过去,等回答生成结束,把完整答案取回来;(2) 按关键字找回历史对话,在里面继续追问,拿到确切答案。复用 Chrome…
git:20260925.32ce6c0 · audit B · 11 stars
claude-remember SKILL.md skill
renky1025/agent-skills · claude-remember/SKILL.md · Review auto-memory entries and produce a report of proposed promotions across the memory hierarchy (project-level…
git:20260925.32ce6c0 · audit A · 11 stars
claude-simplify SKILL.md skill
renky1025/agent-skills · claude-simplify/SKILL.md · Review changed code for reuse, quality, and efficiency, then fix the issues found by launching three parallel review…
git:20260925.32ce6c0 · audit A · 11 stars
clean-code SKILL.md skill
renky1025/agent-skills · clean-code/SKILL.md · Knowledge base distilled from "Clean Code: A Handbook of Agile Software Craftsmanship" by Robert C. Martin (Uncle Bob)…
git:20260925.32ce6c0 · audit A · 11 stars
curriculum-design SKILL.md skill
renky1025/agent-skills · curriculum-design/SKILL.md · 专业输出课程级(教学大纲)与课堂级(教案)双层课程设计方案,遵循 OBE 反向设计与"两性一度"一流课程标准。适用于高校教师教学发展、职业院校课程建设、企业培训课程开发、在线课程设计。触发词:课程设计、教学设计、教学大纲、教案、课程目标、教…
git:20260925.32ce6c0 · audit A · 11 stars
de-ai-writing SKILL.md skill
renky1025/agent-skills · de-ai-writing/SKILL.md · 文本去AI味:用确定性检测与「删除 -> 声纹校准 -> 改写 -> 防过平反查」去除文字的机器腔,把文字放回具体的人身上。产出:静默改写终版或AI味检测报告+七维评分。触发场景:用户说「去AI味」「太像AI写的」「帮我润色得更像人写的」「…
git:20261010.f412a01 · audit A · 11 stars
design-md-extractor SKILL.md skill
renky1025/agent-skills · design-md-extractor/SKILL.md · Extract a visual design system from any website URL and generate a DESIGN.md that strictly follows the…
git:20260925.32ce6c0 · audit A · 11 stars
edulab SKILL.md skill
renky1025/agent-skills · edulab/SKILL.md · 面向中高考数学的可视化解题工具:空间几何题生成可交互 3D 解题演示(建系向量法 + sympy 校验 + Three.js),函数表达式生成参数可控的 2D 图形(滑块实时联动)。产物为单文件自包含交互式…
git:20260925.32ce6c0 · audit A · 11 stars

Every file in renky1025/agent-skills

Browse by kind, by grade A, or by owner.