Skip to main content
NeVibeCode · repository · 155 items

claude-code-agent-monitor: a set by hoangsonww

The hoangsonww/claude-code-agent-monitor repository on GitHub: 155 cards with a description and an install command. Inside: 78 skills, 32 commands and 21 subagents and more. They install into Claude Code, Codex and GitHub Copilot.

Install the whole set
/plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor

About the repository

GitHub
hoangsonww/claude-code-agent-monitor
Stars
★ 1,198
License
MIT
Source updated
2026-10-23
In the catalog since
2026-10-26
webhook-management skill webhook-management is a Claude Code skill that configures CCAM webhook targets, links them to alert rules, and checks delivery records. CX Codex +1 ★ 1,198repo stars remote-collection skill remote-collection — a skill that walks the agent through CCAM remote data sources: connect machines over SSH and pull Claude and Codex history. Useful when sessions live beyond your laptop. CX Codex +1 ★ 1,198repo stars alert-management skill alert-management inspects fired CCAM alerts and manages monitoring rules for token thresholds, inactivity, and status duration. CX Codex +1 ★ 1,198repo stars session-compare skill session-compare is a Claude Code skill that compares two Agent Monitor sessions across costs, tokens, events, and agent activity. It helps investigate why runs had different outcomes. CX Codex +1 ★ 1,198repo stars regression-watch skill regression-watch compares an older baseline window of session history with a recent one and reports which metrics got worse: errors, cache, compactions, cost per session. CX Codex +1 ★ 1,198repo stars pattern-detect skill pattern-detect analyzes agent sessions via Agent Monitor to find recurring tool sequences, error cascades, and delegation habits. Generates a ranked report with recommendations. CX Codex +1 ★ 1,198repo stars optimization-suggest skill The optimization-suggest skill reviews Claude Code session history and ranks ways to cut costs, improve speed, and prevent errors. Use it to plan changes based on recorded activity. CX Codex +1 ★ 1,198repo stars benchmark skill The benchmark skill takes one session or a few recent ones and compares them with the rolling average from Agent Monitor data: cost, tokens, tool count and workflow complexity. Each metric comes back as a percentile of the population. CX Codex +1 ★ 1,198repo stars anomaly-alert skill anomaly-alert flags anomalous Claude Code sessions by checking spending spikes and tool execution errors via local Agent Monitor. CX Codex +1 ★ 1,198repo stars transcript-grep skill transcript-grep is a Claude Code skill that searches session conversations for text or regex and shows matches in context, helping track down prompts, tool calls, or errors. CX Codex +1 ★ 1,198repo stars session-debug skill session-debug — a Claude Code skill that inspects one Agent Monitor session through its event chain, agent tree, and token use. Point it at a session ID, latest, or errors. CX Codex +1 ★ 1,198repo stars hook-diagnostics skill hook-diagnostics troubleshoots Claude Code hook registration, agent monitor reachability, and event ingestion. Useful when events stop appearing in the dashboard. CX Codex +1 ★ 1,198repo stars health-check skill The health-check skill checks Agent Monitor’s API, database, WebSocket, endpoints, hooks, and data freshness. Use it to spot issues in a monitoring setup. CX Codex +1 ★ 1,198repo stars event-trace skill event-trace turns one Claude session into an ordered timeline of its events, flagging gaps, failures and tool calls that never finished. CX Codex +1 ★ 1,198repo stars data-export skill data-export exports Claude Code sessions, events, costs, and analytics into JSON, CSV, or Markdown. Useful for backups, cost auditing, and custom reports. CX Codex +1 ★ 1,198repo stars quick-stats skill quick-stats is a skill that summarizes Agent Monitor sessions, spending, daily events, and tool usage in a compact terminal view. CX Codex +1 ★ 1,198repo stars live-watch skill live-watch polls the Agent Monitor /api/stats endpoint a few times in a row and reports how the counters shift across that window. Useful when you want motion, not a single snapshot. CX Codex +1 ★ 1,198repo stars endpoint-probe skill endpoint-probe is a Claude Code skill that smoke-tests Agent Monitor API routes on localhost, measuring latency and checking JSON response shapes. CX Codex +1 ★ 1,198repo stars dashboard-status skill dashboard-status is a Claude Code skill that checks Agent Monitor API health, session and event counts, WebSocket connections, hooks, and data freshness. It shows whether monitoring is operating. CX Codex +1 ★ 1,198repo stars spend-forecast skill spend-forecast turns the daily session trend on the Agent Monitor dashboard into a spend projection for the end of the week or month. CX Codex +1 ★ 1,198repo stars model-savings skill model-savings estimates potential dollar savings when routing Claude Code runs to cheaper models via Agent Monitor. Handy for pruning token spend. CX Codex +1 ★ 1,198repo stars daily-budget-check skill daily-budget-check is a skill that compares today’s agent-session costs with a daily budget and estimates the spending pace. Check the budget in the morning or evening. CX Codex +1 ★ 1,198repo stars cost-alert skill cost-alert walks through the budget rules configured in Agent Monitor and the alerts that already fired, with a plain explanation of what set each one off. CX Codex +1 ★ 1,198repo stars budget-set skill budget-set translates spend targets into token guardrails and sets up cost alerts on the Agent Monitor dashboard. CX Codex +1 ★ 1,198repo stars skill-inventory skill skill-inventory lists your user and project skills alongside skills contributed by plugins. Use it to spot overlap or trace a skill to the plugin that provides it. CX Codex +1 ★ 1,198repo stars memory-review skill memory-review walks the agent's file-based memory: CLAUDE.md files and per-project auto-memory. Flags facts that went stale or grew too big. CX Codex +1 ★ 1,198repo stars mcp-audit skill Audits user- and project-scoped MCP servers via the Agent Monitor API. Identifies transport issues, duplicate configurations, and external HTTP endpoints. CX Codex +1 ★ 1,198repo stars hook-inventory skill hook-inventory inventories configured hooks and scripts in ~/.claude/hooks, then flags network activity and risky commands. Use it to review hook safety. CX Codex +1 ★ 1,198repo stars config-audit skill config-audit walks your ~/.claude setup and reports what has piled up: skills, subagents, hooks, duplicates and risky shell commands. CX Codex +1 ★ 1,198repo stars usage-trends skill usage-trends tracks Claude Code session history, token consumption, and tool frequency through Agent Monitor API endpoints. Useful for diagnosing agent errors and checking cache efficiency over 365 days. CX Codex +1 ★ 1,198repo stars session-report skill session-report builds a Markdown report for a session or date range, covering model usage, costs, agents, and events. Useful when you need to inspect what happened during a run. CX Codex +1 ★ 1,198repo stars productivity-score skill Turns Agent Monitor metrics into a 0–100 productivity scorecard: session completion, cache efficiency, turn speed, tool success and cost. CX Codex +1 ★ 1,198repo stars model-mix skill model-mix breaks down Claude Code token usage and spend across Opus, Sonnet, and Haiku via Agent Monitor to spot expensive models doing low-complexity tasks. CX Codex +1 ★ 1,198repo stars cost-breakdown skill The cost-breakdown skill reports model and session costs, daily spending trends, and token efficiency. Use it to compare model pricing or plan a budget. CX Codex +1 ★ 1,198repo stars cache-efficiency skill The cache-efficiency skill works out whether prompt caching pays off: hit rate, write-versus-read reuse, and what each side costs in dollars. CX Codex +1 ★ 1,198repo stars

121–155 of 155

More in NeVibeCode

Project sponsors

Companies that keep this analytics open