A test-driven development loop for agentic coding tools such as Claude Code and Codex: /spec, /plan, /implement, with independent review agents that gate the plan before you code and the diff before you commit.
Agent
Adversarial diff reviewer. Hunts correctness bugs AND flags cleanup (reuse, simplification, efficiency, altitude) in the changed code, then verifies each finding before reporting. Runs in an isolated context to eliminate author-evaluator bias. Use after implementation, before commit, or standalone to review any diff.…
Agent
Conformance gate. Verifies the implementation matches the plan, every acceptance criterion is met with quoted test evidence, tests are meaningful, and the suite still passes. Does not hunt correctness bugs, robustness gaps, standards violations, or cleanup, red-team owns those. Use after implementation chunks are…
Agent
Reviews implementation plans for completeness, correctness, functional gaps, standards, regression risk, robustness, architectural gaps, and TDD quality. Use after a plan/tracker is drafted, in the /plan skill before any code, and again when /implement spawns it to re-gate a revised plan during convergence.