debug-live-issue
Debug production-like issues in this repository with disciplined evidence gathering. Use when fixing failing workflows, regressions, flaky behavior, or data…
Import Claude Code or Codex history and move complete CCAM datasets between machines. Use when rescanning provider history, importing a copied directory, uploading JSONL or archives, exporting a backup, restoring it idempotently, or verifying that tokens, workflows, runs, rules,
$ npx -y skills add hoangsonww/Claude-Code-Agent-Monitor --skill history-portability --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/history-portabilityContext preview
The summary Claude sees to decide when to auto-load this skill.
Import Claude Code or Codex history and move complete CCAM datasets between machines. Use when rescanning provider history, importing a copied directory, uploading JSONL or archives, exporting a backup, restoring it idempotently, or verifying that tokens, workflows, runs, rules,
name: history-portability description: > Import Claude Code or Codex history and move complete CCAM datasets between machines. Use when rescanning provider history, importing a copied directory, uploading JSONL or archives, exporting a backup, restoring it idempotently, or verifying that tokens, workflows, runs, rules, and pricing survived.
1. Read provider-specific paths and limits: `ccam import guide --provider claude|codex`. 2. Rescan the configured provider home: `ccam import rescan --provider <provider>`. 3. Scan an existing directory: `ccam import path /absolute/path --provider <provider>`. 4. For file or archive upload, use the app or MCP `dashboard_upload_history_files`.
ccam export ccam-export.json ccam import-data ccam-export.json
Restore is idempotent and non-destructive. Existing sessions are skipped as a whole. New sessions bring agents, events, token usage, and workflows. Independent run, rule, and pricing rows are inserted only when absent.
Verify session counts, representative transcripts, token totals, cost, workflow runs, alert rules, and both Claude and GPT pricing after restore.
🚀 A real-time monitoring dashboard for Claude Code & Codex, built with SQLite3, Node.js, Express, React, Vite, TailwindCSS, & WebSockets. It tracks sessions, agent activity, tool usage, and subagent orchestration, providing live analytics, a Kanban status board, status notifications, a cute buddy, & an interactive web UI/MacOS/Windows native app.
Repo: hoangsonww/Claude-Code-Agent-Monitor
Debug production-like issues in this repository with disciplined evidence gathering. Use when fixing failing workflows, regressions, flaky behavior, or data…
MANDATORY for every coding agent (Claude Code, Codex, or any other) on every change-set — every applicable source file the agent creates or updates MUST start…
MANDATORY for every coding agent and contributor touching localized content — keep all five localization surfaces (dashboard UI keys, wiki page, mirrored…
Operate and maintain the local MCP server for this project. Use when creating MCP host config, troubleshooting tool connectivity, modifying tool domains, or…
Push the current working tree directly to a GitHub PR whose head lives on a **fork**, without creating a new branch and without pushing to `origin` (which is…
Onboard quickly to this repository. Use when asked to understand architecture, locate ownership, choose the right module, or identify the correct commands and…