plan-ceo-review

Reviews plans in CEO mode across four scope strategies with an 11-section deep audit.

Updated Jun 22, 2026
One-click install
npx skills add https://github.com/aicodepro/ai-agent-nexi --skill plan-ceo-review-aicodepro
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: plan-ceo-review
Source: https://github.com/aicodepro/ai-agent-nexi/tree/main/agent/skills/gstack/plan-ceo-review
Command: npx skills add https://github.com/aicodepro/ai-agent-nexi --skill plan-ceo-review-aicodepro

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Plans often suffer from narrow thinking, unchallenged assumptions, and missed risks. This Skill applies a CEO/founder-level review to any plan, challenging premises, expanding or reducing scope deliberately, and running a rigorous multi-section audit before implementation begins. ## Core Features & Use Cases - Four Review Modes: Scope Expansion (dream big), Selective Expansion (hold scope plus cherry-picked expansions), Hold Scope (maximum rigor), and Scope Reduction (strip to essentials). - 11-Section Deep Review: Covers architecture, error and rescue mapping, security threat modeling, data flow edge cases, code quality, tests, performance, observability, deployment, long-term trajectory, and design/UX. - Outside Voice Cross-Check: Automatically runs an independent second opinion via Codex CLI or a Claude subagent, surfacing cross-model tensions for user decision. - Use Case: Before committing to a quarter-long feature build, invoke this Skill to stress-test the plan's ambition, catch silent failure modes, and produce required outputs like a Failure Modes Registry and TODOS.md updates. ## Quick Start Ask the assistant to run a CEO-mode review of your current plan, for example by saying "rethink this plan and tell me if it 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 plan for scope and ambition?

Invoke the plan-ceo-review skill when questioning whether a plan thinks big enough. It offers four modes — Scope Expansion, Selective Expansion, Hold Scope, and Scope Reduction — and walks you through each decision interactively.

What does the 11-section plan review cover?

The review covers architecture, error and rescue mapping, security threat modeling, data flow edge cases, code quality, tests, performance, observability, deployment and rollout, long-term trajectory, and design/UX. No section may be skipped, even if it yields zero findings.

Does plan-ceo-review work with Codex CLI for a second opinion?

Yes, the Outside Voice step runs automatically after the review sections. If Codex CLI is installed and authenticated it runs codex exec; otherwise it falls back to a Claude subagent, and it can be disabled with gstack-config set codex_reviews disabled.

Can the review make code changes to fix findings?

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

When should I not use CEO-mode plan review?

Avoid it for small, well-understood tasks where a full 11-section audit is overkill. It is designed for plans where scope, ambition, or strategic direction is genuinely in question, not routine implementation tickets.