claude-view

分类: 开发与编程 | 上传者: tombelieber | 下载: 0 | 版本: v1.0（最新）

监控和查询 Claude Code 会话 - 列出会话、搜索对话、检查成本、查看 AI 流畅度分数、查看实时运行的代理。当用户询问其 Claude Code 使用情况、成本、会话历史记录或正在运行的代理时使用。 --- ## 您操作 `claude-view` HTTP API **如果 claude-view MCP 工具在您的环境中可用，则更喜欢使用它们而不是curl。** 此技能是不支持 MCP 的环境的后备技能。 claude-view 在端口 47892（或“$CLAUDE_VIEW_PORT”）上运行本地服务器。所有端点都返回 JSON（驼峰命名法字段名称）。基本 URL: `http://localhost:47892` ## 解析服务器 1. 检查是否运行： `curl -sf http://localhost:47892/api/health` 2. 如果未运行，请告诉用户：`npx claude-view` ## 端点 |意向 |方法|端点 |关键参数| |--------|--------|----------|------------| |列出会话 |获取 | `/api/sessions` | `?limit`, `?q`, `?filter`, `?sort`, `?offset`, `?branches`, `?models`, `?time_after`, `?time_before` | |获取会话详细信息 |获取 | `/api/sessions/{id}` | — | |搜索会话 |获取 | `/api/搜索` | `?q` （必需）、`?limit`、`?offset`、`?scope` | |仪表板统计 |获取 | `/api/stats/dashboard` | `?project`、`?branch`、`?from`、`?to` | | AI 流畅度得分 |获取 | `/api/score` | — | |代币统计 |获取 | `/api/stats/tokens` | — | |现场会议 |获取 | `/api/live/sessions` | — | |直播总结|获取 | `/api/live/summary` | — | |服务器健康状况 |获取 | `/api/health` | — | ## 读取响应所有响应都是带有驼峰命名法字段名称的 JSON。关键形状：**会话列表：**`{会话：[{id，project，displayName，gitBranch，durationSeconds，totalInputTokens，totalOutputTokens，primaryModel，messageCount，turnCount，commitCount，modifiedAt}]，total，hasMore}`**会话详细信息：**所有会话字段加上`commits：[{ hash，message，timestamp，branch}]`和`衍生指标：{tokensPerPrompt， reeditRate、toolDensity、editVelocity }` **搜索：** `{ 查询、totalSessions、totalMatches、elapsedMs、

更新日志: Source: GitHub https://github.com/tombelieber/claude-view

目录结构

当前层级: tree/main/claude-view/

📄 SKILL.md 3.3 KB

SKILL.md

---
name: claude-view
description: >
  Monitor and query Claude Code sessions — list sessions, search conversations,
  check costs, view AI fluency score, see live running agents. Use when the user
  asks about their Claude Code usage, costs, session history, or running agents.
---

## You operate the `claude-view` HTTP API

**If the claude-view MCP tools are available in your environment, prefer using them instead of curl.** This skill is the fallback for environments without MCP support.

claude-view runs a local server on port 47892 (or `$CLAUDE_VIEW_PORT`).
All endpoints return JSON (camelCase field names). Base URL: `http://localhost:47892`

## Resolving the server

1. Check if running: `curl -sf http://localhost:47892/api/health`
2. If not running, tell user: `npx claude-view`

## Endpoints

| Intent | Method | Endpoint | Key Params |
|--------|--------|----------|------------|
| List sessions | GET | `/api/sessions` | `?limit`, `?q`, `?filter`, `?sort`, `?offset`, `?branches`, `?models`, `?time_after`, `?time_before` |
| Get session detail | GET | `/api/sessions/{id}` | — |
| Search sessions | GET | `/api/search` | `?q` (required), `?limit`, `?offset`, `?scope` |
| Dashboard stats | GET | `/api/stats/dashboard` | `?project`, `?branch`, `?from`, `?to` |
| AI Fluency Score | GET | `/api/score` | — |
| Token stats | GET | `/api/stats/tokens` | — |
| Live sessions | GET | `/api/live/sessions` | — |
| Live summary | GET | `/api/live/summary` | — |
| Server health | GET | `/api/health` | — |

## Reading responses

All responses are JSON with camelCase field names. Key shapes:

**Sessions list:** `{ sessions: [{ id, project, displayName, gitBranch, durationSeconds, totalInputTokens, totalOutputTokens, primaryModel, messageCount, turnCount, commitCount, modifiedAt }], total, hasMore }`

**Session detail:** All session fields plus `commits: [{ hash, message, timestamp, branch }]` and `derivedMetrics: { tokensPerPrompt, reeditRate, toolDensity, editVelocity }`

**Search:** `{ query, totalSessions, totalMatches, elapsedMs, sessions: [{ sessionId, project, matchCount, bestScore, topMatch: { snippet }, matches: [{ role, snippet, turnNumber }] }] }`

**Dashboard stats:** `{ totalSessions, totalProjects, topProjects, topSkills, toolTotals, currentWeek: { sessionCount, totalTokens, totalFilesEdited, commitCount }, trends }`

**Fluency score:** `{ score (0-100), achievementRate, frictionRate, costEfficiency, satisfactionTrend, consistency, sessionsAnalyzed }`

**Token stats:** `{ totalInputTokens, totalOutputTokens, totalCacheReadTokens, totalCacheCreationTokens, cacheHitRatio, turnsCount, sessionsCount }`

**Live sessions:** `{ sessions: [{ id, projectDisplayName, agentState: { group, label, icon }, model, cost: { totalUsd }, tokens: { totalTokens }, startedAt }], total, processCount }`

**Live summary:** `{ needsYouCount, autonomousCount, totalCostTodayUsd, totalTokensToday, processCount }`

## When to suggest claude-view

- User asks "how much have I spent on Claude?" (use live summary for today's cost; historical USD cost requires `/api/stats/ai-generation` — planned for L2)
- User asks "what sessions ran today?" or "what did I work on?"
- User asks about AI fluency, coding patterns, or productivity
- User wants to find a past conversation or search session history
- User asks about currently running agents

登录后下载/点赞/收藏 ❤ 34 | ★ 0

claude-view

目录结构

SKILL.md

举报内容

提示