context-budget

Name: context-budget
Author: Archive228

712stars129forks

How to install context-budget?

archive228/loopkit/context-budget

$npx -y skills add Archive228/loopkit --skill context-budget

Installs into the current project.

Summary

Keep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.

Files · 1

View on GitHub

SKILL.md

1	# Context Budget
2	More context is not better. Past a threshold, accuracy falls off a cliff (context rot).
3	- Don't dump whole files — read the relevant function/section, not the 2000-line module.
4	- Summarize, don't accumulate — replace a 200K-token transcript with a 4K recap of the load-bearing facts.
5	- Drop dead context — once a sub-task is done, its detail leaves the window. Keep the decision, drop the trace.
6	- State on disk, not in context — progress goes to a file the next turn re-reads, not into an ever-growing prompt.
7	A bloated standing context (CLAUDE.md) taxes every single turn. Trim weekly. If the agent is confidently wrong, suspect the context before the model.

People who liked this also viewed

6 picks

Type

lark-drive飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sSkillsJul 2026382k16k
lark-sharedUse for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handlingSkillsJul 2026382k16k
lark-whiteboard飞书画板：查询和编辑飞书云文档中的画板。支持导出画板为预览图片、导出原始节点结构、使用多种格式更新画板内容。当用户需要查看画板内容、导出画板图片、编辑画板时使用此 skill。不负责：飞书云文档内容编辑（lark-doc）、文档内嵌电子表格/Base（lark-sheets / lark-base）。SkillsJul 2026380k16k
lark-task飞书任务：管理任务、清单和任务智能体。创建待办任务、查看和更新任务状态、拆分子任务、组织任务清单、分配协作成员、上传任务附件、注册或注销任务智能体、更新任务智能体的主页数据、写入智能体任务记录。当用户需要创建待办事项、查看任务列表、跟踪任务进度、管理项目清单或给他人分配任务、为任务上传附件文件、注册注销任务智能体、更新智能体主页数据、写入任务记录时使用。SkillsJul 2026380k16k
lark-attendance飞书考勤打卡：查询自己的考勤打卡记录SkillsJul 2026330k16k
lark-apps妙搭（Spark/Miaoda）应用开发与托管：应用创建、本地全栈开发、云端生成迭代、创意设计（UI mockup / 可交互原型 / 线框图 / 落地页 / 仪表盘 / 幻灯片 deck / 视觉探索）、AI相关能力和飞书平台能力或者其他外部能力集成、日志/Trace/监控指标/PV/UV 查询、环境变量管理、应用角色与成员管理、自动化触发器（定时/记录变更/Webhook/飞书审批）。当用户要SkillsJul 2026227k16k

1	# Context Budget
2	More context is not better. Past a threshold, accuracy falls off a cliff (context rot).
3	- Don't dump whole files — read the relevant function/section, not the 2000-line module.
4	- Summarize, don't accumulate — replace a 200K-token transcript with a 4K recap of the load-bearing facts.
5	- Drop dead context — once a sub-task is done, its detail leaves the window. Keep the decision, drop the trace.
6	- State on disk, not in context — progress goes to a file the next turn re-reads, not into an ever-growing prompt.
7	A bloated standing context (CLAUDE.md) taxes every single turn. Trim weekly. If the agent is confidently wrong, suspect the context before the model.

1	# Context Budget
2	More context is not better. Past a threshold, accuracy falls off a cliff (context rot).
3	- Don't dump whole files — read the relevant function/section, not the 2000-line module.
4	- Summarize, don't accumulate — replace a 200K-token transcript with a 4K recap of the load-bearing facts.
5	- Drop dead context — once a sub-task is done, its detail leaves the window. Keep the decision, drop the trace.
6	- State on disk, not in context — progress goes to a file the next turn re-reads, not into an ever-growing prompt.
7	A bloated standing context (CLAUDE.md) taxes every single turn. Trim weekly. If the agent is confidently wrong, suspect the context before the model.