Agent Pulse
Snapshot recent agent sessions, token usage, model costs, health signals, and forecasts via the Agent Pulse CLI.
Overview
agent-pulse is an agent skill most often used in Operate (also Grow → analytics) that runs Agent Pulse to summarize sessions, tokens, costs, health, and forecasts.
Install
npx skills add https://github.com/jane-o-o-o-o/agent-pulse-skills --skill agent-pulseWhat is this skill?
- Default prompt summarizes sessions, tokens, model costs, health, and forecast
- Invokes agent-pulse binary when on PATH, otherwise python -m agent_pulse.cli
- Subprocess runner with configurable timeout and UTF-8 env defaults
- Returns structured result: command, exit_code, timed_out, parsed JSON when stdout is JSON
- Compact usage snapshot suitable for quick operator checks
Adoption & trust: 11.6k installs on skills.sh; 1 GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You cannot see how your AI-agent sessions, token burn, and model costs trend without manually parsing logs or dashboards.
Who is it for?
Builders who already use Agent Pulse locally and want the agent to run the same inspect command with timeout-safe subprocess handling.
Skip if: Teams without Agent Pulse installed, or anyone needing deep log forensics instead of a summary snapshot.
When should I use this skill?
Use $agent-pulse to summarize recent AI-agent sessions, token usage, model costs, health, and forecast.
What do I get? / Deliverables
You get a compact CLI snapshot the agent can read—structured when JSON—to decide whether usage is healthy or needs intervention.
- Agent Pulse command output (JSON when available)
- Exit status and timeout metadata for the run
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Operating agent-heavy workflows needs visibility into spend and session health without digging through raw logs. Monitoring is the canonical shelf for recurring usage snapshots, timeouts, and JSON output from agent-pulse.
Where it fits
Run a pulse snapshot after a heavy agent refactor week to see if token costs spiked.
Compare forecast output before choosing a cheaper model tier for routine tasks.
Check session health while tuning a long-running agent skill pipeline.
How it compares
Operational snapshot skill, not a hosted observability platform or MCP server.
Common Questions / FAQ
Who is agent-pulse for?
Solo builders and small teams running AI coding agents who want quick session, token, cost, and health summaries through Agent Pulse.
When should I use agent-pulse?
Use it in Operate → monitoring for health checks; in Grow → analytics when reviewing token spend; anytime your default prompt asks to summarize recent agent sessions and forecast usage.
Is agent-pulse safe to install?
It executes local CLI commands and reads environment; review the Security Audits panel on this page and trust only your own agent-pulse installation.
SKILL.md
READMESKILL.md - Agent Pulse
interface: display_name: "Agent Pulse" short_description: "Inspect AI-agent sessions, tokens, model costs, and health." default_prompt: "Use $agent-pulse to summarize my recent AI-agent sessions, token usage, model costs, health, and forecast." """Run a compact Agent Pulse usage snapshot.""" from __future__ import annotations import argparse import json import os import shutil import subprocess import sys def command_base() -> list[str]: if shutil.which("agent-pulse"): return ["agent-pulse"] return [sys.executable, "-m", "agent_pulse.cli"] def run(args: list[str], timeout: int) -> dict: env = os.environ.copy() env.setdefault("PYTHONUTF8", "1") env.setdefault("PYTHONIOENCODING", "utf-8") cmd = command_base() + args try: proc = subprocess.run( cmd, text=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, env=env, check=False, timeout=timeout, ) except subprocess.TimeoutExpired as exc: raw_output = (exc.stdout or "").strip() if isinstance(exc.stdout, str) else "" return { "command": " ".join(cmd), "exit_code": None, "timed_out": True, "timeout_seconds": timeout, "output": raw_output or f"Command timed out after {timeout} seconds.", } raw = proc.stdout.strip() parsed = None if raw: try: parsed = json.loads(raw) except json.JSONDecodeError: parsed = raw return {"command": " ".join(cmd), "exit_code": proc.returncode, "timed_out": False, "output": parsed} def main() -> int: parser = argparse.ArgumentParser(description="Run a compact Agent Pulse JSON snapshot.") parser.add_argument("--hours", type=int, default=24, help="Recent activity window in hours.") parser.add_argument("--days", type=int, default=7, help="Trend/insight window in days.") parser.add_argument("--limit", type=int, default=10, help="Top-session limit.") parser.add_argument( "--command-timeout", type=int, default=20, help="Timeout in seconds for each Agent Pulse subcommand.", ) args = parser.parse_args() hours = str(args.hours) days = str(args.days) limit = str(args.limit) trend_hours = str(args.days * 24) timeout = args.command_timeout snapshot = { "doctor": run(["doctor", "--json"], timeout), f"status_{args.hours}h": run(["status", "--json", "--hours", hours], timeout), "top_cost": run( ["top", "--sort", "cost", "--json", "--hours", trend_hours, "--limit", limit], timeout, ), "models": run(["models", "--json", "--hours", trend_hours], timeout), "leaderboard": run(["leaderboard", "--json", "--hours", trend_hours], timeout), "forecast": run(["forecast", "--json", "--days", days], timeout), "health": run(["health", "--json"], timeout), "score": run(["score", "--json", "--hours", trend_hours], timeout), "budget": run(["budget", "--json"], timeout), "insights": run(["insights", "--json", "--days", days], timeout), } print(json.dumps(snapshot, indent=2, ensure_ascii=False)) return 0 if __name__ == "__main__": raise SystemExit(main()) --- name: agent-pulse description: Use Agent Pulse to inspect local AI-agent activity across Hermes, Claude Code, Codex, DeepSeek, OpenClaw, Copilot, Aider, Qwen, OpenCode, Goose, Cursor, Antigravity, and Amp logs. Use when the user asks about AI-agent sessions, tokens, tool/search calls, model usage, estimated cost, budgets, forecasts, health checks, reports, setup diagnosis, web/API/metrics exports, or MCP integration. --- # Agent Pulse ## Purpose Use the installed `agent-pulse` CLI as the source of truth for local AI-agent activity. The PyPI package is `agentpulse-cli`, while the command remains `agent-pulse`. Prefer running com