Skills for Real Engineers. Straight from my .agents directory.
endpoint-probe
Agent skill fromhoangsonww/Claude-Code-Agent-Monitor
Probes each major Agent Monitor API route — /api/stats, /api/analytics, /api/sessions, /api/pricing/cost, /api/workflows/runs, /api/cc-config/overview — and reports each one's HTTP status, latency, and response shape, flagging which are reachable. Use to verify a dashboard install is wired up correctly.
How to install endpoint-probe
npx skills add hoangsonww/Claude-Code-Agent-Monitor# or add only this skill to Claude Code: copy the folder
plugins/ccam-dashboard/skills/endpoint-probe/
# into
~/.claude/skills/endpoint-probe/ (all projects)
.claude/skills/endpoint-probe/ (one project)
1# Endpoint Probe23Smoke-test the dashboard's main API surface by hitting each major route once and4reporting whether it responds and what shape it returns.56## Input78The user provides: **$ARGUMENTS**910Options: empty (default: probe all routes below), or a substring to filter which11routes are probed (e.g. `pricing` probes only matching routes).1213## Data Sources1415| Endpoint | Returns |16|----------|---------|17| `GET /api/stats` | `{ total_sessions, active_sessions, active_agents, total_agents, total_events, events_today, ws_connections, agents_by_status, sessions_by_status }` |18| `GET /api/analytics` | `{ overview, tokens, tool_usage, daily_events, daily_sessions, agent_types, event_types, avg_events_per_session, total_subagents, sessions_by_status, agents_by_status }` |19| `GET /api/sessions` | Session list; each: `id, status, model, cwd, started_at, ended_at, cost, metadata` |20| `GET /api/pricing/cost` | `{ total_cost, breakdown:[{ model, input_tokens, output_tokens, cache_read_tokens, cache_write_tokens, cost, matched_rule }] }` |21| `GET /api/workflows/runs` | Workflow-tool run journals (fleets) |22| `GET /api/cc-config/overview` | Claude Code config explorer overview (skills, agents, commands, plugins, mcp, hooks, etc.) |2324## Method2526For each route, issue a single `GET` against `http://localhost:4820<path>` with a27short timeout, capturing the HTTP status code, round-trip latency, and the28top-level shape of the JSON body (object keys, or array length). A route counts29…
Excerpt shown under the repository's MIT license.
More skills in Claude-Code-Agent-Monitor
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
