4 Hooks That Let Claude Code Run Autonomously (With Zero Babysitting)

Source: Dev.to

The Problem

Claude Code is powerful, but it stops every few minutes to ask “should I continue?” or “which approach?” In unattended sessions, that means your AI sits idle until you come back.

The Solution

Claude Code Ops Starter – 4 production‑tested Bash hooks that enforce autonomous decision‑making.

What’s Inside

1. Context Monitor (context-monitor.sh)

Counts tool calls as a proxy for context‑window usage. Warns at three thresholds:

• Soft (80) – “Consider deferring large tasks”
• Hard (120) – “Wrap up and hand off”
• Critical (150) – Auto‑generates a checkpoint file for session handoff

# Configurable thresholds
SOFT_WARNING=80
HARD_WARNING=120
CRITICAL=150

2. No‑Ask‑Human (no-ask-human.sh)

Blocks all AskUserQuestion tool calls. Instead of stopping to ask, the AI:

• Decides on its own
• Logs uncertainty to ~/pending_for_human.md
• Moves to the next task

Override with CC_ALLOW_QUESTIONS=1 when you want questions back.

3. Syntax Check (syntax-check.sh)

Auto‑runs verification after every file edit:

• Python: python -m py_compile
• Shell: bash -n
• JSON: jq empty

Catches errors immediately instead of 50 tool calls later. Gracefully skips if jq or python aren’t installed.

4. Decision Warn (decision-warn.sh)

Flags risky commands such as rm -rf, git reset --hard, and DROP TABLE before execution. It warns but doesn’t block – uncomment a line in the script for hard blocking.

Install

git clone https://github.com/yurukusa/claude-code-ops-starter.git
cd claude-code-ops-starter
bash install.sh

No dependencies besides Bash. jq and python are optional (hooks skip gracefully without them).

How It Works

Claude Code has a hooks system that runs shell scripts at specific lifecycle points:

• PreToolUse – runs before a tool call (can block it with exit 1)
• PostToolUse – runs after a tool call (for monitoring and validation)

The starter kit uses both:

Background

These hooks stem from 200+ hours of real autonomous Claude Code operation. Each solved a concrete problem:

• Context monitor – sessions ran out of context without warning.
• No‑ask‑human – overnight sessions left the AI idle for hours waiting for a human answer.
• Syntax check – errors were discovered 50 tool calls after they were introduced.
• Decision warn – a git reset --hard wiped an afternoon of work.

The full setup (multi‑agent orchestration, stall detection, watchdog, task queue, 20+ hooks) is available as the CC‑Codex Ops Kit.

GitHub repository