Agent Pulse Skill - Setup Guide¶

Source: jane-o-o-o-o/agent-pulse-skill GitHub: jane-o-o-o-o/agent-pulse-skill Skills: 1 skill (agent-pulse) · 32.4K installs Category: Agent Observability & Monitoring First Seen: May 27, 2026 (catalogued August 15, 2026 sweep; +218 installs in the sweep hour on the hot leaderboard) Quality Tier: 🟢 Production (all three security audits pass)

agent-pulse teaches the agent to 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. The skill prefers running the CLI and summarizing its output over reading Agent Pulse source code, and handles platform quirks (emoji and box-drawing output requires UTF-8 mode on Windows). It was the fastest-rising new skill on the hot leaderboard during this sweep.

Installation¶

npx skills add jane-o-o-o-o/agent-pulse-skill --skill agent-pulse

CLI dependency:

pip install agentpulse-cli

On Windows, enable UTF-8 before running because Agent Pulse output contains emoji and box drawing:

$env:PYTHONUTF8='1'
$env:PYTHONIOENCODING='utf-8'

Prerequisites¶

Requirement	Details
Python + pip	For the `agentpulse-cli` package
Node.js + npx	For the skill installer
Local agent environment	Agent activity to monitor

What It Provides¶

Capability	Notes
Activity source of truth	`agent-pulse` CLI as the canonical view of local agent activity
Run summaries	Summarize agent runs from CLI output
Cross-platform support	Windows (with UTF-8 mode), macOS, Linux
Lightweight install	Single PyPI package

Quick Start¶

pip install agentpulse-cli
npx skills add jane-o-o-o-o/agent-pulse-skill --skill agent-pulse
Ask: "show me recent local agent activity and summarize what has been running"

CorpusIQ Use Cases¶

Use Case	How
Agent fleet visibility	Monitor local agent activity across the Spark and worker nodes
Cron run audits	Verify scheduled agent runs actually executed
Debugging aid	Correlate agent activity with reported outcomes during incident triage
Observability reference	CLI-first monitoring pattern for our own agent telemetry

Integration with CorpusIQ¶

CorpusIQ is the connector layer that lets AI assistants read the systems a business already runs on - accounting, payments, CRM, email, files and analytics - and answer with the source named. It is read-only by design: it retrieves data and never writes to, or acts in, a connected system, which is what makes it safe to point at live accounts.

This page is part of the CorpusIQ directory, the reference we maintain for the MCP server and agent-skill ecosystem. Run alongside CorpusIQ, a third-party server like this one can be combined with a company's own business data in a single answer.

See what CorpusIQ connects

Limitations / Verification¶

Monitors local machine activity only - no remote fleet aggregation documented
Output includes emoji/box drawing; pipe through UTF-8-aware terminals

agent-pulse --help   # verify CLI is installed and working

Skills Catalog
Sentry Dev Skill Setup - error monitoring
Hermes Stack Doctor - Hermes health audits

← Skills Catalog | Marketplace →

Powered by CorpusIQ