Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/Headless Runner
Run Claude Code in headless/programmatic mode for automation, CI/CD, and agent workflows.
Passed 21 of 23 test cases with the skill, and 10 of 23 without it.
and 15 more in the full report
11 fixed10 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our CI pipeline needs to measure token cost for non-interactive Claude runs. Which specific JSON property returned in JSON mode contains the session cost?
| Checked | Without skill | With skill |
|---|---|---|
| Reads token financial cost from the .cost field of the JSON output | Missed | Passed |
The instructions your model reads when the skill loads.
Run Claude Code programmatically from scripts, CI/CD pipelines, and autonomous agent workflows. Headless mode automatically loads all project configuration (.claude/ directory), giving you full access to skills, agents, hooks, and commands.
Most common usage:
# Basic headless invocation (from project directory)
claude -p "Your prompt here"
# With JSON output for programmatic parsing
claude -p "Run eval baseline for v0.3.14" --output-format json
# Control tool access
claude -p "Analyze failures" --allowedTools "Bash,Read,Grep"
# Multi-turn conversation
claude -p "Start task" --output-format json > result.json
SESSION_ID=$(jq -r '.session_id' result.json)
claude --resume $SESSION_ID "Continue with next step"
What gets loaded automatically:
.claude/settings.json and .claude/settings.local.json.claude/agents/ (all project agents).claude/skills/ (all project skills).claude/commands/Invoke this skill when user asks about:
test cases passed, vs 10 / 23 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.