gepetto

Malicious tool definition detected

If neither CLI is available, gepetto will skip the external review step and continue with the workflow. ## Resuming If the workflow is interrupted (context limit, need a break), just re-run with the same spec: ``` /gepetto @planning/auth-spec.md ``` gepetto detects existing files and resumes from where it left off.

Malicious tool definition detected

Tool: references/external-review.md Description: # External Review Protocol This step sends `claude-plan.md` to external LLMs (Gemini and Codex) for independent review using CLI subagents.

Malicious tool definition detected

Tool: references/research-protocol.md Description: # Research Protocol This document defines the research decision and execution flow.

Malicious tool definition detected

Tool: references/section-index.md Description: # Section Index Creation Create `<planning_dir>/sections/index.md` to define implementation sections.

Malicious tool definition detected

``` ## Parallel Execution Strategy **Launch one subagent per section in a single message** for maximum parallelization: ``` ┌─────────────────────────────────────────────────────┐ │ PARALLEL SUBAGENT APPROACH │ │ │ │ 1.

Tool passed security scan

Malicious tool definition detected

Tool: SKILL.md [2/2] Description: (what must be true when complete) - Dependencies (requires/blocks) - Implementation details (from the plan) - Acceptance criteria (checkboxes) - Files to create/modify The implementer should NOT need to reference any other document.

Tool passed security scan