claude-code-complete-agent/examples/13-auto-mode/prompt.md

Example 13: Auto Mode

Let Claude Code run autonomously with an AI safety classifier reviewing every action. No manual approvals needed. This is the feature that makes Claude Code feel like OpenClaw's daemon mode.

OpenClaw equivalent: Default autonomous mode with Docker sandbox + exec approvals for dangerous commands.

Requirements:

• Claude Code v2.1.86+
• Team plan or higher (research preview)

Enabling Auto Mode

From the CLI:

claude --enable-auto-mode

In an active session, press Shift+Tab to cycle through permission modes until you reach Auto Mode.

The prompt

Clone the repository at https://github.com/example/sample-app,
install dependencies, run the test suite, fix any failing tests,
and create a summary of what you changed in CHANGES.md.

What happens

1. Claude Code clones the repo (no permission prompt)
2. Runs npm install (no permission prompt)
3. Runs npm test (no permission prompt)
4. Reads failing test output, edits source files (no prompt)
5. Re-runs tests until they pass (no prompt)
6. Writes CHANGES.md (no prompt)

Every action is reviewed by the safety classifier (Sonnet 4.6) before execution. If an action is flagged as risky (e.g., mass file deletion, data exfiltration), it is blocked and Claude is redirected to take a different approach.

How the safety classifier works

Two-layer system:

1. Fast filter: Quick yes/no on the action category
2. Chain-of-thought: Detailed reasoning for borderline cases

Performance (Anthropic's internal testing):

• 0.4% false positive rate (safe actions incorrectly blocked)
• 5.7% false negative rate (risky actions not caught)

The classifier runs on Sonnet 4.6 regardless of your session model.

Permission mode comparison

Mode	Approvals	Safety	Use case
Default	Every action	Maximum	Learning, sensitive projects
Auto-edit	Pre-approved patterns	High	Known workflows
Auto Mode	AI classifier	High	Autonomous execution
Bypass	None	Minimal	Sandboxed environments only

How this compares to OpenClaw

OpenClaw runs autonomously by default. Safety comes from Docker sandboxing (container limits what the agent can do even if it tries something dangerous).

Claude Code Auto Mode runs autonomously with an AI classifier reviewing each action before execution. Safety comes from pre-execution screening, not post-execution containment.

Different philosophy:

• OpenClaw: "Let it try, contain the damage" (sandbox)
• Claude Code: "Review before executing" (classifier)

Both have trade-offs. Sandboxes catch unknown threats. Classifiers prevent the action from happening at all but may miss novel attacks (5.7% false negative rate).

---

Now Try It Yourself

Auto Mode works best for well-defined, bounded tasks. Try it on something safe first:

[With Auto Mode enabled]
Read all markdown files in this project. Create a table of contents
in pipeline-output/index.md listing every file with a one-line
description. Verify the file count matches.

The pattern you just learned: Auto Mode removes the permission prompts. Use it when you trust the task scope and want Claude to work without interruption. Start with read-heavy, write-light tasks and expand as you build confidence.

When to use Auto Mode:

• Research tasks where you trust the search and write scope
• File organization within a known project
• Running a tested pipeline end-to-end without babysitting
• Batch processing files with a predictable pattern

When NOT to use Auto Mode:

• First time running an untested pipeline
• Tasks that touch production systems or external APIs
• Anything involving credentials, payments, or irreversible actions