Agentic OS Runner — Development skill for Claude Code
Background daemon + hook + metric-pull templates.
How to install Agentic OS Runner
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open cth9191/agentic-os-runner and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agentic OS Runner does
Background daemon + hook + metric-pull templates. Code companion for a private Obsidian agentic-OS build guide.
Alternatives in Development
- Private Company Research — 未上市公司研究:多Agent并行深度研究框架 15.9k ★
- North Star Metric — Define North Star Metric and input metrics constellation 7.8k ★
- Financial Services Plugins — Plugins that turn Claude into a specialist for financial services — investment banking, equity research, priva 7.7k ★
README
agentic-os-runner
Code companion for a build guide that wires Obsidian + Claude Code into a personal agentic operating system.
This repo contains the orchestration plumbing — the background daemon, the activity-logging hook, and metric-pull script templates. **It is incomplete on its own.** The build guide (separate, paywalled inside the Chase AI+ Skool community) explains the vault layout, daily-note schema, MCP wiring, skill design, and Obsidian plugin that make these pieces useful.
If you're following the guide, clone this repo as instructed and the guide tells Claude Code where each piece lives.
Contents
runner/
runner.js # Node daemon — watches the vault's intent queue,
# spawns headless `claude -p` subprocesses, writes
# run records back to the vault.
# Parallel pool (MAX_CONCURRENT=3) + serial-skill
# + dedupe-skill gates.
start-runner.vbs # Windows launcher (drop in Startup folder)
start-runner.sh # macOS / Linux launcher
package.json
hooks/
activity-log.js # PostToolUse hook — appends Claude's tool calls
# to today's daily note's `## Activity Log` section.
# Cross-process atomic file lock.
settings.example.json # Snippet to merge into ~/.claude/settings.json
package.json
metric-scripts/
_common.py # Shared helpers: CSV append, snapshot write, env loader
pull_template_api.py # Template — REST API metric pull
pull_template_scrape.py# Template — Playwright scrape metric pull
pull_template_local.py # Template — read a local file as a metric
run_all.ps1 # Windows wrapper — runs every pull_*.py in parallel
run_all.sh # macOS / Linux wrapper
Installation
The build guide walks through each step in order. Quick reference for paid members already following along:
# Clone
git clone https://gi
Related Skills
Clawdmeter Plus
A round AMOLED desk display for your live Claude Code usage, weather, background-agent health, and a daily voi
Anima
new Native macOS companion for Claude Code. Per-project ASCII familiars, nim token economy, cross-session watc
Agentic Kit
One command to install, heal & prove ruflo (claude-flow) + agentic-qe + RuvNet Brain — plus ambidextrous Claud
Loopgen Rs
Agentic loop runner for Claude Code — turns a goal into an iterative claude -p loop with a LOOP_STATUS termina
MCP Daemon Diet
One shared MCP daemon per machine instead of a stdio copy in every agent session: recipe, autostart templates
Clooks
new Persistent hook daemon that replaces per-invocation spawning -- 112x faster hooks with batching, dependenc
Related Agents
E2e Specs
E2E test agent that creates Playwright end-to-end tests from a plan's requirements. Tests drive the dashboard
Brain Keeper
Maintains Agentic SEO project authorial brain pages, append-only log, source provenance, and Obsidian-compatib
Fagan
External PR review agent. Invoke as a background task to produce a structured findings report for a pull reque