plan-ceo-review

Reviews development plans through an 11-section CEO-mode scope and rigor audit.

Updated Sep 13, 2026
One-click install
npx skills add https://github.com/abdulazeezoj/monovella-poc --skill plan-ceo-review-abdulazeezoj
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: plan-ceo-review
Source: https://github.com/abdulazeezoj/monovella-poc/tree/main/.agents/skills/gstack/plan-ceo-review
Command: npx skills add https://github.com/abdulazeezoj/monovella-poc --skill plan-ceo-review-abdulazeezoj

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Plans often ship with unchallenged assumptions, narrow scope, or missing edge-case coverage. This Skill runs a structured CEO/founder-mode review that challenges premises, evaluates scope ambition, and walks every finding through explicit user decisions before the plan is finalized. ## Core Features & Use Cases - Four review modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope plus cherry-picked additions), HOLD SCOPE (maximum rigor), and SCOPE REDUCTION (strip to essentials). - 11-section deep review: architecture, error and rescue mapping, security threat model, data flow edge cases, code quality, tests, performance, observability, deployment, long-term trajectory, and design/UX, each producing findings decided via structured AskUserQuestion briefs. - Outside voice cross-check: runs an independent second opinion via the Codex CLI (or a fallback subagent) and surfaces cross-model disagreements for the user to resolve. - Use Case: Before implementing a new feature plan, invoke the review to stress-test the architecture diagram, map every failure path, and decide interactively whether the scope is ambitious enough. ## Quick Start Ask the assistant to run a CEO-mode review of the current plan and challenge whether the scope is ambitious enough.

Frequently Asked Questions about plan-ceo-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I review a development plan before implementing it?

Invoke the plan-ceo-review skill against the plan file. It walks through 11 review sections covering architecture, error handling, security, tests, performance, and rollout, presenting each finding as a decision you approve or reject before the plan is finalized.

What review modes does plan-ceo-review support?

Four modes: SCOPE EXPANSION for dreaming bigger, SELECTIVE EXPANSION for holding scope while cherry-picking additions, HOLD SCOPE for maximum rigor on the current plan, and SCOPE REDUCTION for stripping to essentials. The mode is agreed with the user at the start.

Does plan-ceo-review modify code during the review?

No. The skill is review-only and explicitly forbids code changes. Every finding is presented through an AskUserQuestion decision brief, and changes land in the plan only after explicit user approval.

Can I get a second AI opinion on my plan review?

Yes. The skill runs an outside-voice pass using the Codex CLI by default, falling back to a fresh subagent if Codex is unavailable. Cross-model disagreements are surfaced as tension points for the user to decide.

When should I not use plan-ceo-review?

Skip it for routine coding tasks, obvious changes, or when a plan has already been through the review and only implementation remains. It is designed for high-stakes plan scrutiny, not turn-level coding decisions.