Local Agent Onboarding Doctor v1.0 Release Notes
What it does
Local Agent Onboarding Doctor converts redacted first-run setup notes into a deterministic local agent onboarding diagnostic. It helps teams check whether runtime, model routing, memory, tool calling, health, fallback, and rollback evidence is strong enough before adoption. It is advisory and read-only, so the output supports review and release workflows without acting as an approval authority.
It is built for marketplace buyers who need a quick, repeatable way to inspect redacted evidence without changing runtime, configuration, billing, deployment, memory, or finance-system state.
Use cases
- Platform teams onboarding local agents who need a repeatable evidence check before rollout.
- Implementation leads who want setup gaps surfaced as PASS, REVIEW, BLOCKED, or ERROR.
- Support teams that need a read-only way to review redacted setup claims without touching configuration.
Requirements
- Python 3 with standard-library support.
- OpenClaw workspace with the skill installed.
- Redacted local notes supplied via
--textor--notes. - No API keys required; the analyzer is local and read-only.
- Recommended OpenClaw version: current stable release.
Example usage
python3 scripts/local_agent_onboarding_doctor.py --text "redacted evidence with owner, validation, rollback plan, health check, and review timestamp" --json
Expected output: JSON with a verdict such as PASS, REVIEW, BLOCKED, or ERROR, a numeric evidence score, findings for missing or risky signals, and mutated_files: []. Strong evidence commonly covers runtime version, model identifier, provider route, memory path, tool calling check, structured output check, health check, fallback plan, and rollback plan.
Price
$4.99