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 renky1025/agent-skills --skill workbuddy-context-handoffgit clone --depth 1 https://github.com/renky1025/agent-skillsWrote 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/renky1025/agent-skills/workbuddy-context-handoff)<a href="https://agentmods.dev/skills/renky1025/agent-skills/workbuddy-context-handoff"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/workbuddy-context-handoff/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/renky1025/agent-skills/workbuddy-context-handoff"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/workbuddy-context-handoff.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00157 | $0.02220 |
| Opus 5.5 | $0.00063 | $0.00888 |
| Sonnet 5.5 | $0.00031 | $0.00444 |
| Haiku 4.5 | $0.00016 | $0.00222 |
Grade A, and why
workbuddy-context-handoff 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 23d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
- 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。 - 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。 - 注册 hooks(合并进 settings 的
hooks键,不要整体覆盖):
"hooks": {
"Stop": [
{ "hooks": [ { "type": "command", "command": "<abs>/run-hook.sh <abs>/handoff-trigger.mjs", "timeout": 15 } ] }
],
"SessionStart": [
{ "matcher": "startup|clear",
"hooks": [ { "type": "command", "command": "<abs>/run-hook.sh <abs>/handoff-resume.mjs", "timeout": 15 } ] }
]
}
- 校验 JSON:用
JSON.parse解析整个 settings 文件,确认其余键未丢。 - 实测触发:手动复现单个 hook ——
echo '<payload json>' | /bin/bash -lc '<command>', 再跑一轮真实会话确认 handoff 产出与注入都发生。 - 清理测试产物:删掉
hooks/state/与handoffs/下的测试文件。
Decision Rules
- 触发点只能选 Stop:它是唯一能强制模型继续的事件;注入点只能选 SessionStart:它的 stdout
或
hookSpecificOutput.additionalContext是唯一能进新会话上下文的位置。PreCompact 不能当 handoff 触发器(stdout 只进压缩指令,exit 2 只给用户看消息)。 - 阈值调整优先级:先看是不是被内置 50% pre-message 压缩截断 —— 开桌面端 Max Mode,
或设
CODEBUDDY_PRE_MESSAGE_COMPACT_PCT=80;确认能到目标比例后,再调handoff.config.json里的 handoff 阈值。 - contextWindow 兜底顺序:
handoff.config.json.contextWindow留 null 时依次取settings.autoCompactWindow->CODEBUDDY_AUTO_COMPACT_WINDOW->200000。 - 需要确认事件名 / matcher 语义 / hook 入参 / 阈值常量 -> 读
references/runtime-facts.md。 - 要写或改 hook 脚本本身 -> 读
references/hook-implementation.md。 - hook 不触发 / 到不了阈值 / 搜不到字符串 -> 见
## Troubleshooting。
What ships with it
2 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.
- 23d ago First seen · 132 lines · 157 tokens per session scan A c3dc386450ef
workbuddy-context-handoff is a skill published in the GitHub repository renky1025/agent-skills (11 stars, last pushed 8d ago), licensed MIT. It adds 157 tokens to every session and 2,220 once invoked, about $0.0006 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 2026-09-25.
Other skills, from other repositories
project-wiki
A system for creating and maintaining a project wiki: a set of organized documents that explain a software project's plans, rules, references, and progress.
mindos-zh
A local knowledge-base assistant for storing and finding decisions, meeting notes, procedures, troubleshooting lessons, and preferences across conversations and coding agents. It works only with the MindOS knowledge base.
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
mindos-max
MindOS: local knowledge assistant & global memory layer. Keeps decisions, notes, SOPs, debugging lessons, architecture choices, research findings, preferences, conversation summaries for all connected agents. PROACTIVE: (1) search MindOS first for past context, (2) offer to save after valuable work, (3) persist key…
mindos
Operate a MindOS knowledge base: update notes, search, organize files, execute SOPs/workflows, retrospective, append CSV, cross-agent handoff, route unstructured input to the right files, distill experience, sync related docs. Use when the task targets files inside the user's MindOS KB (mindRoot). NOT for editing app…
plugin-core-builtin-migration
A repeatable process for turning an optional MindOS renderer plugin into a built-in, always-available part of the application. It also covers moving old entry points while keeping existing data usable.