Skill · v1.0
Plan Challenger
Plan Challenger is a skill for surfacing the hard questions before a plan goes into execution. Five structured angles (strategic fit, timing, baked-in assumptions, architectural risk, opportunity cost) produce sharp observations and a one-line verdict. Not a veto. A mirror.
Install
Claude Code (CLI / WSL / Git Bash)
/plugin marketplace add https://www.infinitegameos.io/marketplace.json
/plugin install plan-challenger@igos-libraryClaude Code (VS Code)
Install in VS CodeOpens the Claude Code plugins dialog with the marketplace and skill prefilled. Requires the Claude Code VS Code extension installed and signed in. Or paste the snippet below into .claude/settings.json for VS Code, JetBrains or any setup that prefers manual config.
{
"extraKnownMarketplaces": {
"igos-library": {
"source": {
"source": "url",
"url": "https://www.infinitegameos.io/marketplace.json"
}
}
},
"enabledPlugins": {
"plan-challenger@igos-library": true
}
}Direct markdown URL (Claude Code, Cursor, Codex CLI)
https://www.infinitegameos.io/markdown/skills/plan-challengerCursor (.mdc rules file)
curl -O https://www.infinitegameos.io/install/cursor/plan-challenger.mdcAider, Cline, any agent with --read
curl -O https://www.infinitegameos.io/markdown/skills/plan-challenger
aider --read plan-challenger.mdDefinition
Plan Challenger runs an adversarial pre-build pass on any plan before execution begins. It is a discipline, not a tool. Five angles work the plan systematically: strategic fit, timing, baked-in assumptions, architectural risk, opportunity cost. Each angle produces one to three sharp observations or questions, not a checklist of every concern. The output is a five-angle challenge report plus near-call decisions plus a one-line verdict (Proceed, Revise [specific element] or Pause [specific reason]). The verdict is a recommendation, not a gate. The operator decides what moves forward.
The five angles
Strategic Fit: is this the right problem for this moment? What competes for the slot? Does this plan advance the operator's primary arc, or branch sideways?
Timing: why now? What changes if deferred two weeks? Is the urgency real or inherited from habit?
Baked-In Assumptions: what must be true for this plan to succeed that has not been verified? Each assumption gets a risk rating of low, medium or high.
Architectural Risk: what is the most likely way this plan breaks or creates debt? What looks fine on paper but creates pain in six months?
Opportunity Cost: what are we not doing by doing this? What capability or momentum is being paused or sacrificed?
Use Cases
Pre-execution sanity check on a multi-week plan
Before kicking off a multi-week implementation, the operator runs Plan Challenger on the written plan. The five angles surface a baked-in assumption that would have collapsed Week 3. The plan revises before commit; Week 3 lands as intended.
Resolving close-call scope decisions
Two framings for scope are both defensible. Plan Challenger surfaces the close call rather than collapsing to a single answer. The operator sees the trade explicitly and decides with full visibility instead of arbitrating in the moment.
High-stakes plans with confidence scoring
For high-stakes plans, the optional confidence scoring rubric (0-100) runs over each finding. Findings below 50 are notes; findings at 75 or above earn a named action in the verdict. The operator sees ranked severity instead of a flat list of objections.
FAQ
Does Plan Challenger replace operator judgment?
No. The verdict is a recommendation, not a gate. The skill surfaces the hard questions; the operator decides what moves forward. Even a Pause verdict can be overridden if the operator has context the skill could not see.
How is this different from generic plan review?
Generic review produces a list of concerns. Plan Challenger produces five angles plus a one-line verdict, with optional confidence scoring for severity ranking. The structure forces depth in each angle rather than breadth across many.
When should the optional confidence scoring be used?
Use it when the five angles produce many findings and you need a ranked view before deciding. On straightforward plans, qualitative assessment is sufficient. The scoring layer is optional, not default.
Plan Challenger pairs naturally with Pending Plan Implementation. Challenge the plan, then execute. If you want the design frame for which plans are worth running in the first place, the Sovereign Life Playbook is the upstream architecture.
See the Sovereign Life Playbook