context-budget-analyzer
Skill4 starsChanged 32 days agoNo licenceView on GitHub
Agent 上下文预算分析器。扫描一次 Agent 会话的对话记录、Transcript 或手工提供的 上下文清单,按"系统指令 / 任务目标 / 约束 / 工具输出 / 对话历史 / 中间推理 / 状态与记忆"分类统计 Token 占用,识别上下文污染与 Compaction 风险: 超长工具输出、重复粘贴内容、失效假设、约束丢失风险,并给出分层治理建议 (原文保留 / 结构化 / 留指针 / 可丢弃)。约束审计会解析压缩摘要行,对照 判定每条约束是"被压缩丢弃"还是"被摘要救回",直答"压缩丢掉了什么"。 触发词:分析上下文,上下文预算,Token 都花在哪了,上下文为什么这么长, 压缩会丢什么,context budget,analyze context,context usage, token breakdown,compaction risk,会话太长了,上下文污染, 上下文增长,usage 轨迹,context growth,compaction 检测,工具 schema 利用率, tool schema utilization,加载未用的工具, 约束丢失,约束审计,constraint audit,governance decay, 压缩丢掉了什么,压缩摘要对照,compaction diff, OpenClaw trajectory,轨迹分析,run-based。 NOT for: 模型参数量估算、API 计费账单分析、Prompt 写作优化。
In this repository13 other files it gives its agents.
- code-review-ProMaxSkill
- delivery-spec-auditSkill
- dev-mentorSkill
- english-assessmentSkill
- fe-cliSkill
- project-doc-analystSkill
- project-onboardingSkill
- rednote-creatorSkill
- renovation-143mSkill
- screenshot-to-promptSkill
- skill-creator-ProMaxSkill
- skill-review-proSkill
- todo-list-promaxSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.