Skip to content
Back to search

claude-code-agent-monitor-plugins

MarketplaceWorks with Claude CodeGitHub

Official Claude Code plugin marketplace for CCAM with 14 plugins, 66 skills, 18 agents, 34 commands, and comprehensive local dashboard operations.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/hoangsonww/Claude-Code-Agent-Monitor with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/hoangsonww/Claude-Code-Agent-Monitor'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/hoangsonww-claude-code-agent-monitor/badge.svg)](/listings/hoangsonww-claude-code-agent-monitor)

HTML

<a href="/listings/hoangsonww-claude-code-agent-monitor"><img src="/api/listings/hoangsonww-claude-code-agent-monitor/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Prerequisites

- **Node.js** >= 22.22.0 (24 LTS recommended) - **npm** >= 9.0.0

1. Install

git clone https://github.com/hoangsonww/Claude-Code-Agent-Monitor.git
cd Claude-Code-Agent-Monitor
npm run setup

2. Configure Claude Code Hooks

npm run install-hooks

The installer opens an interactive multi-select: use arrow keys, <kbd>Space</kbd>, and <kbd>Enter</kbd> to choose **Claude Code**, **Codex (beta)**, or both (Claude Code is preselected). Claude Code entries live in `~/.claude/settings.json`; Codex entries live in `~/.codex/hooks.json`. If a selected dashboard hook set already exists, it warns before replacing only this dashboard's entries — unrelated hooks are preserved. You can make the same selection later in **Settings → Hook Configuration → Install hooks**.

On first dashboard entry, choose the data source and the app checks hook readiness only for that selection. Claude Code requires Claude hooks, Codex requires Codex hooks, and Both requires both hook sets. When every required hook set is already installed, the dashboard opens immediately. Otherwise the setup gate lists and installs only the missing selected providers, while preserving unrelated hooks and letting a failed status check fall back safely to manual setup.

Codex rollouts in `~/.codex/sessions` are also discovered continuously. The dashboard reads their append-only JSONL incrementally, prioritizes the newest rollouts, and isolates a bad historical file for retry, so sessions, tokens, costs, conversation rows, and WebSocket updates stay current even if a hook notification is missed.

Codex rollout lifecycle records drive the same live card states as Claude Code: `user_message` and `task_started` mark the main agent **Working**; `task_complete` leaves the session active but shows **Waiting**; and `turn_aborted` shows **Waiting** with an interrupted reason. A new rollout record self-heals an erroneously completed session. On supported local hosts, liveness is matched to the exact `rollout-*.jsonl` held open by each Codex process, so old rollouts that share a project directory are imported as completed instead of appearing as phantom active agents. The Node launcher and its native Codex child are collapsed into one logical process, so one TUI produces one card.

Codex `/rename` titles are read from its native session index and update session and agent cards in real time. Its conversation replay includes human turns plus `exec` custom-tool calls and outputs, with cursor pagination that loads older messages at the top of the transcript.

Claude Code and Codex cards show a compact, two-row history of their latest distinct human prompts beneath the provider-native title, so a short friendly name or terse follow-up never hides the active task. Claude refreshes this context from its local transcript cache during live hooks, imports, and watchdog sweeps; Codex refreshes it from rollout records and falls back to persisted `user_message` events for older imports. The transcript renders persisted PNG/JPEG/GIF/WebP attachments for Claude Code and Codex when available, while duplicate Codex response/event copies collapse into one human turn.

Codex `response_item` tool invocations are indexed once through a dedicated rollout cursor, so its Workflows tool flow, session drill-in, model/token totals, and `context_compacted` counts reflect the recorded Codex data without replaying lifecycle or token counters. In a Codex-only dashboard scope, the Claude Code-only Dynamic Workflows journal panel is hidden rather than presented as empty Codex data.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 91 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. {
  2. "name": "claude-code-agent-monitor-plugins",
  3. "description": "Official Claude Code plugin marketplace for CCAM with 14 plugins, 66 skills, 18 agents, 34 commands, and comprehensive local dashboard operations.",
  4. "owner": { "name": "hoangsonww", "url": "https://github.com/hoangsonww" },
  5. "plugins": [
  6. {
  7. "name": "ccam-analytics",
  8. "source": "./plugins/ccam-analytics",
  9. "description": "Deep analytics and monitoring for Claude Code sessions — cost tracking, token usage breakdowns, usage trends, and productivity scoring powered by Agent Monitor.",
  10. "tags": ["analytics", "tokens", "cost", "productivity"]
  11. },
  12. {
  13. "name": "ccam-config",
  14. "source": "./plugins/ccam-config",
  15. "description": "Audit and govern your Claude Code configuration and file-based memory via the Agent Monitor Config Explorer API — skills, subagents, commands, MCP servers, hooks, settings, and the per-project memory store. Surfaces sprawl, duplication, risky hooks, and stale facts, all read through the dashboard at http://localhost:4820.",
  16. "tags": ["config", "memory", "governance", "mcp"]
  17. },
  18. {
  19. "name": "ccam-cost-guard",
  20. "source": "./plugins/ccam-cost-guard",
  21. "description": "Budget tracking, spend forecasting, and cost-threshold alerts for Claude Code usage via the Agent Monitor pricing engine. Watches spend against a target budget, projects month-end cost from the daily trend, surfaces the priciest sessions, estimates savings from cheaper-model routing, and wires up cost alert rules — all backed by the dashboard at http://localhost:4820.",
  22. "tags": ["budget", "cost", "forecast", "alerts"]
  23. },
  24. {
  25. "name": "ccam-dashboard",
  26. "source": "./plugins/ccam-dashboard",
  27. "description": "Direct MCP integration with the Claude Code Agent Monitor dashboard — real-time session data access, quick stats, and dashboard health monitoring via Model Context Protocol.",
  28. "tags": ["dashboard", "status", "mcp", "connector"]
  29. },
  30. {
  31. "name": "ccam-devtools",
  32. "source": "./plugins/ccam-devtools",
  33. "description": "Developer tools for Claude Code Agent Monitor — session debugging, hook diagnostics, data export, and system health checks for maintaining a healthy monitoring setup.",
  34. "tags": ["devtools", "debug", "diagnostics", "export"]
  35. },
  36. {
  37. "name": "ccam-insights",
  38. "source": "./plugins/ccam-insights",
  39. "description": "AI-powered insights for Claude Code — pattern detection, anomaly alerting, optimization recommendations, and session comparison using Agent Monitor analytics.",
  40. "tags": ["insights", "patterns", "anomaly", "optimization"]
  41. },
  42. {
  43. "name": "ccam-integrations",
  44. "source": "./plugins/ccam-integrations",
  45. "description": "Manage CCAM alert rules, universal webhook providers, browser push notifications, and SSH Remote Data Sources with explicit mutation and external-send confirmation.",
  46. "tags": ["alerts", "webhooks", "push", "remote-sources", "ssh", "integrations"]
  47. },
  48. {
  49. "name": "ccam-platform",
  50. "source": "./plugins/ccam-platform",
  51. "description": "Administer CCAM's Claude Code and Codex configuration explorers, provider-aware history import, backup restore, hook installation, home directories, updates, and MCP server.",
  52. "tags": ["claude-code", "codex", "config", "hooks", "import", "backup"]
  53. },
  54. {
  55. "name": "ccam-productivity",
  56. "source": "./plugins/ccam-productivity",
  57. "description": "Productivity workflows for Claude Code — daily standups, weekly reports, sprint summaries, and intelligent workflow optimization powered by Agent Monitor session data.",
  58. "tags": ["productivity", "reports", "workflows", "standup"]
  59. },
  60. {
  61. "name": "ccam-quality",
  62. "source": "./plugins/ccam-quality",
  63. "description": "Reliability and error monitoring for Claude Code sessions — surfaces APIError events, hook delivery failures, tool-failure ratios (PreToolUse/PostToolUse gaps), and SLO tracking with error-budget reporting, all derived from the Claude Code Agent Monitor event stream at http://localhost:4820.",
  64. "tags": ["reliability", "errors", "slo", "quality"]
  65. },
  66. {
  67. "name": "ccam-reports",
  68. "source": "./plugins/ccam-reports",
  69. "description": "Generate stakeholder-ready CCAM reports from local session, cost, reliability, and workflow data with explicit scope, evidence, and export-friendly Markdown.",
  70. "tags": ["reports", "executive-summary", "cost", "reliability", "workflows", "ccam"]
  71. },
  72. {
  73. "name": "ccam-runner",
  74. "source": "./plugins/ccam-runner",
  75. "description": "Operate dashboard-launched Claude Code and Codex runs with safe launch, follow-up, stop, resume, model discovery, and persistent run-history workflows.",
  76. "tags": ["claude-code", "codex", "run", "launcher", "resume", "agents"]
  77. },
  78. {
  79. "name": "ccam-sessions",
  80. "source": "./plugins/ccam-sessions",
  81. "description": "Search, inspect, replay, and manage Claude Code sessions tracked by the Agent Monitor dashboard — find sessions by project, model, status, or date; reconstruct event timelines; walk transcripts turn-by-turn; roll up activity per working directory; and identify stale or empty sessions before cleanup.",
  82. "tags": ["sessions", "search", "transcript", "replay"]
  83. },
  84. {
  85. "name": "ccam-workflows",
  86. "source": "./plugins/ccam-workflows",
  87. "description": "Analyze multi-agent orchestration and Workflow-tool fleet runs — DAGs, delegation, concurrency, error propagation, and effectiveness — via the Agent Monitor workflow intelligence API at http://localhost:4820. Maps parent→child subagent edges, scores model delegation and subagent success, surfaces concurrency lanes and serialization bottlenecks, and traces error cascades by agent depth.",
  88. "tags": ["workflows", "orchestration", "subagents", "fleet"]
  89. }
  90. ]
  91. }
README.md · README · 203 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Agent Dashboard for Claude Code, Cursor & Codex
  2. ### A local-first control room for AI coding agents
  3. Monitor Claude Code, Cursor, and Codex sessions in real time. Follow conversations and tools, inspect agent hierarchies, understand token usage and cost, analyze orchestration, and operate local agents from one responsive dashboard.
  4. > [!TIP]
  5. > **Complete guides:** [English](./README-EN.md) · [中文](./README-CN.md) · [Tiếng Việt](./README-VN.md) · [한국어](./README-KO.md) · [Español](./README-ES.md)
  6. ![Claude Code](https://img.shields.io/badge/Claude_Code-orange?style=flat-square&logo=claude&logoColor=white)
  7. ![Cursor](https://img.shields.io/badge/Cursor-111827?style=flat-square&logo=cursor&logoColor=white)
  8. ![OpenAI Codex](https://img.shields.io/badge/OpenAI_Codex-blue?style=flat-square&logo=githubcopilot&logoColor=white)
  9. ![Claude Code Plugins](https://img.shields.io/badge/Claude_Code_&_Codex-Plugins_&_Skills-orange?style=flat-square&logo=anthropic&logoColor=white)
  10. ![Model Context Protocol](https://img.shields.io/badge/Model_Context_Protocol-1.0-0f766e?style=flat-square&logo=modelcontextprotocol&logoColor=white)
  11. ![Node.js](https://img.shields.io/badge/Node.js-%3E%3D22.22-339933?style=flat-square&logo=node.js&logoColor=white)
  12. ![Python](https://img.shields.io/badge/Python-%3E%3D3.6-3776AB?style=flat-square&logo=python&logoColor=white)
  13. ![Express](https://img.shields.io/badge/Express-4.21-000000?style=flat-square&logo=express&logoColor=white)
  14. ![ws](https://img.shields.io/badge/ws-WebSocket_server-010101?style=flat-square&logo=socketdotio&logoColor=white)
  15. ![web-push](https://img.shields.io/badge/web--push-VAPID-3b82f6?style=flat-square&logo=javascript&logoColor=white)
  16. ![swagger-ui-express](https://img.shields.io/badge/swagger--ui--express-5.0-85EA2D?style=flat-square&logo=swagger&logoColor=white)
  17. ![multer](https://img.shields.io/badge/multer-multipart_upload-FF6B6B?style=flat-square&logo=express&logoColor=white)
  18. ![adm-zip](https://img.shields.io/badge/adm--zip-archive_extract-FBBF24?style=flat-square&logo=files&logoColor=white)
  19. ![tar](https://img.shields.io/badge/tar-tgz_extract-A78BFA?style=flat-square&logo=gnu&logoColor=white)
  20. ![Commander CLI](https://img.shields.io/badge/Commander_CLI-14-F05032?style=flat-square&logo=gnubash&logoColor=white)
  21. ![React](https://img.shields.io/badge/React-19.2-61DAFB?style=flat-square&logo=react&logoColor=white)
  22. ![TypeScript](https://img.shields.io/badge/TypeScript-5.7-3178C6?style=flat-square&logo=typescript&logoColor=white)
  23. ![Javascript](https://img.shields.io/badge/JavaScript-ES6-F7DF1E?style=flat-square&logo=javascript&logoColor=white)
  24. ![Vite](https://img.shields.io/badge/Vite-7.3-646CFF?style=flat-square&logo=vite&logoColor=white)
  25. ![Tailwind CSS](https://img.shields.io/badge/Tailwind_CSS-3.4-06B6D4?style=flat-square&logo=tailwindcss&logoColor=white)
  26. ![PostCSS](https://img.shields.io/badge/PostCSS-8.5-DD3A0A?style=flat-square&logo=postcss&logoColor=white)
  27. ![Autoprefixer](https://img.shields.io/badge/Autoprefixer-10.4-DD3735?style=flat-square&logo=autoprefixer&logoColor=white)
  28. ![React Router](https://img.shields.io/badge/React_Router-8.3-CA4245?style=flat-square&logo=reactrouter&logoColor=white)
  29. ![Lucide](https://img.shields.io/badge/Lucide_Icons-0.474-F56565?style=flat-square&logo=lucide&logoColor=white)
  30. ![D3.js](https://img.shields.io/badge/D3.js-7-F9A03C?style=flat-square&logo=d3&logoColor=white)
  31. ![Mermaid](https://img.shields.io/badge/Mermaid-10.2-ff3333?style=flat-square&logo=mermaid&logoColor=white)
  32. ![i18next](https://img.shields.io/badge/i18next-22.4-7A42FF?style=flat-square&logo=i18next&logoColor=white)
  33. ![i18next Language Detector](https://img.shields.io/badge/i18next_Language_Detector-6.1-7A42FF?style=flat-square&logo=i18next&logoColor=white)
  34. ![SQLite](https://img.shields.io/badge/SQLite-3-003B57?style=flat-square&logo=sqlite&logoColor=white)
  35. ![better--sqlite3](https://img.shields.io/badge/better--sqlite3-11.7-003B57?style=flat-square&logo=sqlite&logoColor=white)
  36. ![better-sqlite3 WAL](https://img.shields.io/badge/better--sqlite3-WAL_mode-003B57?style=flat-square&logo=sqlite&logoColor=white)
  37. ![WebSocket](https://img.shields.io/badge/WebSocket-RFC_6455-010101?style=flat-square&logo=socketdotio&logoColor=white)
  38. ![SSE](https://img.shields.io/badge/SSE-Server_Sent_Events-FF6600?style=flat-square&logo=googlechrome&logoColor=white)
  39. ![OpenAPI](https://img.shields.io/badge/OpenAPI-3.0-000000?style=flat-square&logo=openapiinitiative&logoColor=white)
  40. ![Swagger](https://img.shields.io/badge/Swagger-3.0-85EA2D?style=flat-square&logo=swagger&logoColor=white)
  41. ![VS Code](https://img.shields.io/badge/VS_Code-Extension-007ACC?style=flat-square&logo=vscodium&logoColor=white)
  42. ![Electron](https://img.shields.io/badge/Electron-35-47848F?style=flat-square&logo=electron&logoColor=white)
  43. ![electron-builder](https://img.shields.io/badge/electron--builder-25.1-2c2e3b?style=flat-square&logo=electron&logoColor=white)
  44. ![macOS](https://img.shields.io/badge/macOS-Desktop_App-000000?style=flat-square&logo=apple&logoColor=white)
  45. ![Windows](https://img.shields.io/badge/Windows-Desktop_App-0078D6?style=flat-square&logo=windows&logoColor=white)
  46. ![SMAppService](https://img.shields.io/badge/SMAppService-Login_Items-000000?style=flat-square&logo=apple&logoColor=white)
  47. ![macOS DMG](https://img.shields.io/badge/macOS_DMG-arm64_%2B_x64-7c3aed?style=flat-square&logo=apple&logoColor=white)
  48. ![NSIS Installer](https://img.shields.io/badge/Windows-NSIS_%2B_Portable-1f6feb?style=flat-square&logo=windows&logoColor=white)
  49. ![Vitest](https://img.shields.io/badge/Vitest-1.0-646CFF?style=flat-square&logo=vitest&logoColor=white)
  50. ![React Testing Library](https://img.shields.io/badge/React_Testing_Library-13.0-FF5733?style=flat-square&logo=testinglibrary&logoColor=white)
  51. ![ESLint](https://img.shields.io/badge/ESLint-8.44-4B32C3?style=flat-square&logo=eslint&logoColor=white)
  52. ![Prettier](https://img.shields.io/badge/Prettier-3.8-F7B93E?style=flat-square&logo=prettier&logoColor=white)
  53. ![Docker](https://img.shields.io/badge/Docker-20.10-2496ED?style=flat-square&logo=docker&logoColor=white)
  54. ![Podman](https://img.shields.io/badge/Podman-4.0-CC342D?style=flat-square&logo=podman&logoColor=white)
  55. ![Open Container Initiative](https://img.shields.io/badge/Open_Container_Initiative-OCI-000000?style=flat-square&logo=opencontainersinitiative&logoColor=white)
  56. ![Prometheus](https://img.shields.io/badge/Prometheus-3.13-E6522C?style=flat-square&logo=prometheus&logoColor=white)
  57. ![Grafana](https://img.shields.io/badge/Grafana-13.1-F46800?style=flat-square&logo=grafana&logoColor=white)
  58. ![Terraform](https://img.shields.io/badge/Terraform-%3E%3D1.7-844FBA?style=flat-square&logo=terraform&logoColor=white)
  59. ![Kubernetes](https://img.shields.io/badge/Kubernetes-%3E%3D1.29-326CE5?style=flat-square&logo=kubernetes&logoColor=white)
  60. ![Helm](https://img.shields.io/badge/Helm-4-0F1689?style=flat-square&logo=helm&logoColor=white)
  61. ![Kustomize](https://img.shields.io/badge/Kustomize-5.0-326CE5?style=flat-square&logo=kubernetes&logoColor=white)
  62. ![Nginx](https://img.shields.io/badge/Nginx-Ingress-009639?style=flat-square&logo=nginx&logoColor=white)
  63. ![Coralogix](https://img.shields.io/badge/Coralogix-Observability-1a1a2e?style=flat-square&logo=datadog&logoColor=white)
  64. ![OpenTelemetry](https://img.shields.io/badge/OpenTelemetry-Collector-4f46e5?style=flat-square&logo=opentelemetry&logoColor=white)
  65. ![AWS](https://img.shields.io/badge/AWS-ECS%20%7C%20RDS-232F3E?style=flat-square&logo=task&logoColor=white)
  66. ![Google Cloud](https://img.shields.io/badge/Google_Cloud-GKE%20%7C%20SQL-4285F4?style=flat-square&logo=googlecloud&logoColor=white)
  67. ![Azure](https://img.shields.io/badge/Azure-AKS%20%7C%20SQL-0078D4?style=flat-square&logo=cloudflare&logoColor=white)
  68. ![Oracle Cloud](https://img.shields.io/badge/Oracle_Cloud-OKE%20%7C%20DB-F80000?style=flat-square&logo=cloudways&logoColor=white)
  69. ![GitHub Actions](https://img.shields.io/badge/GitHub_Actions-pipelines-2088FF?style=flat-square&logo=githubactions&logoColor=white)
  70. ![Make](https://img.shields.io/badge/Make-4.3-000000?style=flat-square&logo=make&logoColor=white)
  71. ![Auto Release](https://img.shields.io/badge/CI-auto--release_to_GitHub-22c55e?style=flat-square&logo=githubactions&logoColor=white)
  72. ![MIT License](https://img.shields.io/badge/License-MIT-yellow?style=flat-square)
  73. <p align="center">
  74. <a href="images/analytics.png"><img src="images/readme/analytics.png" alt="CCAM dashboard with live agent and session activity" width="100%"></a>
  75. <br>
  76. <em>Live fleet state, active work, recent events, cost, and system health.</em>
  77. </p>
  78. ## See what your agents are doing
  79. CCAM combines native hooks with provider-aware transcript discovery. It stays local by default and turns agent activity into a searchable, durable operational record.
  80. - **One live fleet:** Claude Code, Cursor, and Codex sessions appear in the same Dashboard, Sessions, Activity Feed, and Kanban views.
  81. - **Complete conversations:** Rendered Markdown, highlighted code, tool calls, command output, queued prompts, attachments, and provider-native titles; Cursor adopts a generated title only when ingestion metadata proves the current fallback is CCAM-owned.
  82. - **Agent orchestration:** Parent-child trees, background agents, dynamic workflow runs, tool-flow graphs, concurrency, delegation, and compaction analysis.
  83. - **Cost and usage:** API-equivalent estimate details live behind the cost label's info icon; Cursor usage is counted once per generation against the concrete native model.
  84. - **Run and resume agents:** Launch Claude Code or Codex, stream output, send follow-ups, resume previous work, and reattach to background runs.
  85. - **Configuration visibility:** Inspect Claude Code and Codex settings, skills, hooks, MCP servers, rules, plugins, memory, profiles, and instructions.
  86. - **Operational safety:** Loopback binding, optional authentication, guarded mutations, backup-first edits, bounded uploads, and no automatic self-update.
  87. - **Team-ready delivery:** Desktop applications, containers, Kubernetes, Terraform, monitoring, alerts, webhooks, and remote data sources.
  88. ## See CCAM in action
  89. <p align="center">
  90. <a href="images/session-conversation.png"><img src="images/readme/session-conversation.png" alt="Rendered agent conversation with code and tool activity" width="100%"></a>
  91. <br>
  92. <em>Conversation history with code, tools, reasoning, and session context.</em>
  93. </p>
  94. <p align="center">
  95. <a href="images/workflows.png"><img src="images/readme/workflows.png" alt="Workflow and orchestration analytics" width="100%"></a>
  96. <br>
  97. <em>Workflow intelligence for orchestration, delegation, tools, errors, and concurrency.</em>
  98. </p>
  99. <p align="center">
  100. <a href="images/config.png"><img src="images/readme/config.png" alt="Claude Code and Codex configuration explorers" width="100%"></a>
  101. <br>
  102. <em>Provider-aware configuration, skills, hooks, plugins, MCP, rules, and memory.</em>
  103. </p>
  104. <p align="center">
  105. <a href="images/run.png"><img src="images/readme/run.png" alt="Run Agent provider selection" width="100%"></a>
  106. <br>
  107. <em>Launch and manage Claude Code or Codex without leaving the dashboard.</em>
  108. </p>
  109. ## Quick start
  110. **Requirements:** Node.js 22.22 or newer and npm 9 or newer.
  111. ```bash
  112. git clone https://github.com/hoangsonww/Claude-Code-Agent-Monitor.git
  113. cd Claude-Code-Agent-Monitor
  114. npm run setup
  115. npm run dev
  116. ```
  117. Open [http://localhost:5173](http://localhost:5173). `npm run setup` installs the root, client, and VS Code extension dependencies, builds the MCP server, and links the `ccam` CLI. On first launch, follow the dashboard prompt to install hooks for the providers you select, or run `npm run install-hooks` manually.
  118. For production, run `npm run build && npm start` and open [http://localhost:4820](http://localhost:4820).
  119. Before an upgrade that may recount usage, capture and compare read-only cost snapshots:
  120. ```bash
  121. node scripts/cost-snapshot.js snapshot --out before.tsv
  122. # Upgrade and restart CCAM, then let startup maintenance finish.
  123. node scripts/cost-snapshot.js snapshot --out after.tsv
  124. node scripts/cost-snapshot.js compare before.tsv after.tsv --fail-on-local-change
  125. ```
  126. Keep these TSV files private because they contain session identifiers and ownership metadata. The guard fails when an existing local session's usage or cost changes, ownership moves to or from local, or a local session disappears; remote and newly added sessions are reported separately. See the [complete upgrade safeguard](./README-EN.md#cost-snapshots-before-an-upgrade) for the exact compared fields.
  127. ## Choose how to run CCAM
  128. | Option | Best for | Guide |
  129. | --- | --- | --- |
  130. | Source checkout | Development and local customization | [Full setup guide](./README-EN.md#quick-start) |
  131. | Desktop app | A persistent macOS or Windows app with tray controls | [Desktop guide](./DESKTOP.md) |
  132. | Docker or Podman | Isolated local or server deployments | [Deployment guide](./DEPLOYMENT.md) |
  133. | Kubernetes or Terraform | Production infrastructure | [Deployment reference](./docs/DEPLOYMENT.md) |
  134. | MCP sidecar | Agent-driven dashboard queries and guarded operations | [MCP guide](./mcp/README.md) |
  135. ## Extensions and automation
  136. CCAM ships **14 plugins**, **66 plugin skills**, **18 Claude subagents**, **34 Claude commands**, and **77 total repository skills** across Claude Code and Codex formats.
  137. ```bash
  138. claude plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor
  139. codex plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor
  140. npx skills add hoangsonww/Claude-Code-Agent-Monitor --list
  141. ```
  142. The `ccam` CLI and local MCP server expose sessions, agents, events, transcripts, analytics, pricing, workflows, alerts, imports, configuration, remote sources, and maintenance operations for humans and automation.
  143. ## Documentation
  144. - **Complete product and operational reference:** [README-EN.md](./README-EN.md)
  145. - **Documentation index:** [docs/README.md](./docs/README.md)
  146. - **Task-oriented handbook:** [GitHub Wiki](https://github.com/hoangsonww/Claude-Code-Agent-Monitor/wiki)
  147. - **Localized product tour:** [Static Wiki](https://hoangsonww.github.io/Claude-Code-Agent-Monitor/wiki/)
  148. - **Architecture:** [ARCHITECTURE.md](./ARCHITECTURE.md)
  149. - **CLI:** [docs/CLI.md](./docs/CLI.md)
  150. - **REST and OpenAPI:** [docs/API.md](./docs/API.md)
  151. - **Hooks and lifecycle:** [docs/HOOKS.md](./docs/HOOKS.md)
  152. - **Database:** [docs/DATABASE.md](./docs/DATABASE.md)
  153. - **Plugins:** [docs/PLUGINS.md](./docs/PLUGINS.md)
  154. - **MCP:** [docs/MCP.md](./docs/MCP.md) and [mcp/README.md](./mcp/README.md)
  155. - **Desktop application:** [DESKTOP.md](./DESKTOP.md) and [desktop/README.md](./desktop/README.md)
  156. - **Deployment:** [DEPLOYMENT.md](./DEPLOYMENT.md) and [docs/DEPLOYMENT.md](./docs/DEPLOYMENT.md)
  157. - **Security:** [.github/SECURITY.md](./.github/SECURITY.md)
  158. ## Local-first and secure by default
  159. The dashboard binds to `127.0.0.1` by default. It does not require cloud credentials, and it does not transmit your transcripts or agent data to a hosted service. Optional tokens protect HTTP, WebSocket, hook, MCP, and remote-push surfaces when you deliberately expose them beyond loopback.
  160. See the [security policy](./.github/SECURITY.md) and [full configuration reference](./README-EN.md#configuration) before enabling remote access.
  161. ## Contributing and support
  162. - Read the [contributing guide](./.github/CONTRIBUTING.md).
  163. - Report bugs through [GitHub Issues](https://github.com/hoangsonww/Claude-Code-Agent-Monitor/issues).
  164. - Ask questions and share ideas in [GitHub Discussions](https://github.com/hoangsonww/Claude-Code-Agent-Monitor/discussions).
  165. - Follow the [Code of Conduct](./.github/CODE_OF_CONDUCT.md).
  166. ## License
  167. MIT. See [LICENSE](./LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.