菜单
Roll up Claude Code sessions by working directory (project) from Agent Monitor data — session count, total cost, total tokens, and last-active timestamp per cwd — so per-project activity can be compared at a glance. Use when summarizing where effort and spend went across projects.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/hoangsonww/Claude-Code-Agent-Monitor --skill cwd-rollup命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Generate a comprehensive session report with per-model token usage (input, output, cache_read, cache_write including compaction baselines), cost breakdown via the pricing engine, tool invocations, agent hierarchy, compaction events, API errors, turn durations, and thinking block counts. Use when reviewing a specific session or summarizing activity over a date range.
Choose and apply the correct semantic version bump for this repository. Use for every user-visible release, before merge when a change set should ship as patch, minor, or major, and whenever package/plugin/desktop version metadata must stay synchronized.
Choose and apply the correct semantic version bump for this repository. Use for every user-visible release, before merge when a change set should ship as patch, minor, or major, and whenever package/plugin/desktop version metadata must stay synchronized.
基于 SOC 职业分类
| name | cwd-rollup |
| description | Roll up Claude Code sessions by working directory (project) from Agent Monitor data — session count, total cost, total tokens, and last-active timestamp per cwd — so per-project activity can be compared at a glance. Use when summarizing where effort and spend went across projects. |
Aggregate session activity per working directory (project).
The user provides: $ARGUMENTS
top N → keep only the N highest-cost (or highest-count) projects.| Endpoint | Returns |
|---|---|
GET /api/run/cwds | the distinct working directories that have sessions — the rollup key set |
GET /api/sessions?limit=N | session list: id, status, model, cwd, started_at, ended_at, cost, metadata (usage_extras with token counts) |
GET /api/pricing/cost | fleet cost: total_cost, breakdown[{ model, input_tokens, output_tokens, cache_read_tokens, cache_write_tokens, cost, matched_rule }] — for the fleet total to compute each cwd's share |
GET /api/run/cwds for the canonical list of working directories. Apply the
$ARGUMENTS filter (substring match) if one was given.
GET /api/sessions?limit=1000. Bucket sessions by cwd.
For each working directory compute:
cost field across the bucket.usage_extras (sum the four into a total, and keep input + output as the
"billable text" subtotal).started_at (or ended_at) in the bucket.GET /api/pricing/cost for total_cost; show each cwd's cost as a percentage of the
fleet total.
Sort by cost descending by default (or count if the user asked); apply top N.
Markdown table: project (cwd basename) | sessions | total tokens | cost | % of fleet | last active | models.
Currency as USD to 4 decimal places; token counts with thousands separators; sort
cost-descending. Add a final TOTAL row summing the columns. Only count tokens that
the session metadata actually carries — if usage_extras is absent for a session,
note it as excluded rather than guessing. If the dashboard is unreachable, tell the
user to start it with npm start from the repo root.