Adversarial Task Plan Review — Productivity skill for Claude Code
Adversarially review a generated per-task plan file before implementation begins.
How to install Adversarial Task Plan Review
Installs to ~/.claude/commands/thibautbaissac-react-express-ai-kit-adversarial-task-plan-review.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/ThibautBaissac/react-express-ai-kit/HEAD/.claude/commands/adversarial-task-plan-review.md -o ~/.claude/commands/thibautbaissac-react-express-ai-kit-adversarial-task-plan-review.md Restart Claude Code, or start a new session, for it to be picked up.
What Adversarial Task Plan Review does
name: adversarial-task-plan-review description: Adversarially review a generated per-task plan file before implementation begins. argument-hint: "[task-number]" arguments: [task]
**Task selector:** `$task` is the task number passed to this command (for example, `/adversarial-task-plan-review 2`). Everything below targets `tasks/task-$task.md`. If no task number was passed, treat the task number as `1`.
You are an adversarial per-task planning reviewer. Your job is to review the
Alternatives in Productivity
- Reviews Plans — Review all active architecture plans relevant to the current task 15.6k ★
- New Task — Analyze task complexity and create actionable implementation plan 1.5k ★
- Trio — Force a trio review of the task that follows — pm, designer, and engineer weigh in in parallel before any acti 324 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Adversarial Specs Review
Adversarially review a Claude-produced overall task decomposition before any per-task implementation planning
Adversarial Execution
Adversarial Execution — an execution-time review gate: two independent strong models must both prove your work
MCP Tasks Review Task Implementation
Review the implementation of a task before completion
Plan Review
Create an implementation plan and automatically review it for the following task:
Axiom Planning
TDD-validated implementation planning with a four-reviewer plan-review quality gate - atomic-task plans with e
Eval Swarm
Fan every eval- evaluator agent across slices of the monorepo as a parallel swarm via the eval-swarm workflow
Related Agents
Task Plan Verifier
Phase 4 - LLM-as-judge verification of task definitions during planning. Evaluates tasks against spec, strateg
Validate Agent
You are a specialized validation agent. Your job is to validate a technical plan's technology choices against
Bug Repro Triager.Agent
Converts bug reports, logs, and stack traces into reproducible steps, suspected root causes, and a minimal inv