claude-code-headless
Scannednpx machina-cli add skill aiskillstore/marketplace/claude-code-headless --openclawFiles (1)
SKILL.md
3.2 KB
Claude Code Headless Mode
Run Claude Code from scripts without interactive UI.
Quick Start
# Basic headless execution
claude -p "Explain this code" --allowedTools "Read,Grep"
# JSON output for parsing
claude -p "List files" --output-format json
# Continue conversation
claude -p "Start analysis" --output-format json > result.json
session=$(jq -r '.session_id' result.json)
claude --resume "$session" "Now fix the issues"
Essential CLI Options
| Flag | Description |
|---|---|
-p, --print | Non-interactive (headless) mode |
--output-format | text, json, stream-json |
-r, --resume | Resume by session ID |
-c, --continue | Continue most recent session |
--allowedTools | Comma-separated allowed tools |
--disallowedTools | Comma-separated denied tools |
--mcp-config | Path to MCP server config JSON |
--verbose | Enable verbose logging |
--append-system-prompt | Add to system prompt |
Permission Modes
| Mode | Flag | Effect |
|---|---|---|
| Default | (none) | Prompt for permissions |
| Accept edits | --permission-mode acceptEdits | Auto-accept file changes |
| Bypass | --permission-mode bypassPermissions | Skip all prompts |
Output Formats
Text (default)
claude -p "Hello"
# Outputs: Human-readable response
JSON
claude -p "Hello" --output-format json
{
"type": "result",
"subtype": "success",
"result": "Hello! How can I help?",
"session_id": "abc123",
"total_cost_usd": 0.001,
"duration_ms": 1234,
"num_turns": 1
}
Stream-JSON
claude -p "Hello" --output-format stream-json
# Real-time JSONL output for each message
Common Patterns
Script with tool restrictions
claude -p "Analyze the codebase" \
--allowedTools "Read,Grep,Glob" \
--disallowedTools "Write,Edit,Bash"
CI/CD integration
claude -p "Review this PR diff" \
--permission-mode acceptEdits \
--output-format json \
--append-system-prompt "Focus on security issues"
Multi-turn automation
session=$(claude -p "Start task" --output-format json | jq -r '.session_id')
claude --resume "$session" "Continue with step 2"
claude --resume "$session" "Finalize and report"
Error Handling
result=$(claude -p "Task" --output-format json)
if [[ $(echo "$result" | jq -r '.is_error') == "true" ]]; then
echo "Error: $(echo "$result" | jq -r '.result')" >&2
exit 1
fi
Official Documentation
- https://code.claude.com/docs/en/headless - Headless mode reference
- https://code.claude.com/docs/en/settings - Settings and permissions
Additional Resources
./references/cli-options.md- Complete CLI flag reference./references/output-formats.md- Output format schemas./references/integration-patterns.md- CI/CD and scripting examples
See Also: claude-code-hooks for automation events, claude-code-debug for troubleshooting
Source
git clone https://github.com/aiskillstore/marketplace/blob/main/skills/0xdarkmatter/claude-code-headless/SKILL.mdView on GitHub Overview
Claude Code Headless Mode lets you run Claude Code from scripts without an interactive UI. It enables non-interactive execution with JSON or stream outputs and supports session-based multi-turn conversations, making automation, CI/CD, and scripting workflows practical.
How This Skill Works
The CLI uses -p/--print for headless execution and --output-format to select text, json, or stream-json. You can resume conversations with -r/--resume and continue with -c/--continue, while --allowedTools and --disallowedTools restrict what tools can be used in automation.
When to Use It
- Automating code explanations or reviews in CI/CD pipelines without a UI
- Parsing Claude's structured responses in scripts using --output-format json or stream-json
- Running multi-turn analyses across steps by resuming a session
- Enforcing tool restrictions in automation with --allowedTools/--disallowedTools
- Integrating Claude Code into PR or code-review automation workflows
Quick Start
- Step 1: claude -p "Explain this code" --allowedTools "Read,Grep"
- Step 2: claude -p "List files" --output-format json
- Step 3: session=$(jq -r '.session_id' result.json); claude --resume "$session" "Now fix the issues"
Best Practices
- Use non-interactive mode (-p/--print) for scripts and automation
- Prefer JSON or stream-json output to simplify parsing with jq or similar tools
- Leverage --resume and --continue for orchestrated multi-turn tasks
- Limit capabilities in CI with --allowedTools/--disallowedTools
- Capture and log total_cost_usd, duration_ms, and session_id from outputs
Example Use Cases
- CI job that explains a code snippet and parses the result in JSON
- Multi-turn code analysis across steps using a shared session
- List files and parse results in a downstream step
- Review PR diffs with a security-focused prompt and augmented system prompt
- Fail-fast script that checks is_error and exits with a non-zero status
Frequently Asked Questions
Add this skill to your agents