Stats
Actions
Tags
From resilient-flows
Fresh adversarial review of implementation plans before execution. Dispatches a read-only agent to challenge feasibility, find gaps, and surface unstated assumptions. Bounded to 2 review passes. Use after writing a plan and before starting implementation.
How this skill is triggered — by the user, by Claude, or both
Slash command
/resilient-flows:adversarial-plan-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
After writing an implementation plan, challenge it with a fresh perspective before committing to execution. This catches feasibility gaps, missing edge cases, and unstated assumptions that the planner (you) may be anchored to.
After writing an implementation plan, challenge it with a fresh perspective before committing to execution. This catches feasibility gaps, missing edge cases, and unstated assumptions that the planner (you) may be anchored to.
superpowers:writing-plans or manual planning)Ensure the plan exists as a readable artifact (file or task description). The reviewer needs the full plan, not a summary.
Launch a read-only Agent with this framing:
You are a fresh reviewer seeing this plan for the first time.
You have NO ownership of it and NO anchoring bias.
Review the plan at [path/location] for:
1. **Feasibility gaps**: Are there steps that assume something unverified?
(API exists, library supports X, performance will be acceptable)
2. **Missing edge cases**: What happens when inputs are empty, huge,
concurrent, or malformed? What about error paths?
3. **Unstated assumptions**: What does the plan take for granted that
should be explicitly verified or decided?
4. **Ordering risks**: Are there steps that depend on earlier steps
but don't say so? Could parallel execution cause conflicts?
5. **Scope creep signals**: Are there steps that go beyond the
original requirement?
For each concern:
- State it as a specific question, not vague worry
- Reference the specific plan step
- Rate: BLOCKING (must resolve before execution) or ADVISORY (worth noting)
If the plan is solid, say so explicitly — do NOT invent concerns
to appear thorough.
| Finding type | Action |
|---|---|
| No concerns (plan is solid) | Proceed to execution |
| ADVISORY only | Note them, proceed to execution |
| BLOCKING concerns (pass 1) | Revise the plan to address them, then run one more review |
| BLOCKING concerns (pass 2) | Present unresolved concerns to user for decision |
npx claudepluginhub thamam/a2x-marketplace --plugin resilient-flowsGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.