claude-session-observability
Skill3 starsChanged 8 days agoApache-2.0View on GitHub
当要看本机各窗口与子孙代理在跑什么、并发几路、按单按模型花了多少,或要起运行看板、调价目与报警阈值、查规矩报警时使用。凡遇到这些情况,先读本 skill 再动手:先起看板看图,别凭印象报数;看板只覆盖 Claude Code 会话记录。
In this repository25 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- closeout-report-draftingSkill
- context-guard-hooksSkill
- contract-and-test-infraSkill
- doc-pointer-checkSkill
- engineering-pitfalls-checklistSkill
- first-window-requirementsSkill
- frontend-integration-preflightSkill
- hive-dispatchSkill
- legacy-project-onboardingSkill
- memory-index-foldingSkill
- memory-writingSkill
- merge-and-deploySkill
- open-source-preflightSkill
- pointer-handoffSkill
- repo-scale-reportingSkill
- shared-checkout-safetySkill
- short-book-draftingSkill
- subtraction-reviewSkill
- ticket-desk-usageSkill
- top-audit-dispatchSkill
- verify-agent-claimsSkill
- window-handoff-draftingSkill
- zero-window-taskbook-draftingSkill
The file
Files
这个 skill 是干什么的(人话)
这个 skill 帮你起本机运行看板,看清每扇窗和子孙代理树谁在跑、跑了多久、并发几路、按单花了多少。它教怎么起、看哪几块、价目与报警阈值在哪改;数字以看板为准,不凭印象报。不用它,常见的坑是把 codex / zcode 的窗也当成已统计、价目没配就把花费当真、或漏看了哪扇窗其实早就空转。
分类
分类:装 core/ 即可用
用前填这几个名字
- {{看板启动命令}}:起运行看板的命令,在仓根跑;例:python -X utf8 core/tools/dashboard/server.py(隔离模式再加 -I,两种起法行为一致)。
有 python 用 python;没有时将启动命令的 python -X utf8 换成 py -X utf8,其余参数(含 -I)不变。
什么时候用
- 开工或中途要看现在有几扇窗、几个子孙代理在跑,有没有卡住或空转。
- 要报并发路数、代理时长、按单或按模型汇总的花费。
- 规矩报警响了,要定位是哪扇窗、哪条规矩触的。
- 要调模型单价、计费口径或报警阈值。
- 要看历史统计,或给窗口起别名、写备注。
步骤
- 装法:只拷产品 core/ 一个目录,把 core/desk_config.json 的「办公目录」改成自己的路径即可用;纯标准库,无需装包、无需联网。
- 起看板:在仓根跑 {{看板启动命令}},实际地址以终端输出为准(端口被占会依次顺延);终端按 Ctrl+C 停止。可选 --port 只试指定端口、--open 服务就绪后打开浏览器;Windows 可双击 core/tools/dashboard/启动看板.bat。工单台服务已起时,顶栏「运行看板」在新标签打开站内页,与工单台同端口、同进程,不占工单接口。
- 看什么:项目、窗口、子孙代理树、代理时间轴、在跑并发、按模型与按单汇总、规矩报警与历史统计。
- 记住覆盖范围:只覆盖 Claude Code 会话记录,codex / zcode 窗不在内;数据源只读 ~/.claude/projects,不改会话记录、不展示对话正文。隔离运行时可加 --cache-dir 指定数据缓存下的隔离子目录。
- 调配置:价目在 core/tools/dashboard/配置/价目.json,计费口径在 core/tools/dashboard/配置/计费口径.json,报警阈值在 core/tools/dashboard/配置/报警阈值.json,运行时随扫描重载,改完不用重启;窗口别名与备注由页面保存,首次保存才创建,不随产品分发。
- 细节以 core/tools/dashboard/README.md 为准,两边对不上以它为准。
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.

