Implementation Review

Run this before every commit, after /verify. The goal: what was planned is implemented, what is implemented is tested, and what is tested is correct.

Each of the seven checks is run by a dedicated subagent. Spawn all seven in parallel, collect their reports, then synthesise into the output format below. Never run the checks sequentially in the main agent, spawn then collect then synthesise.

Two checks pull in other skills' content, pass it into the subagent brief:

• Checks 2-4 apply /testing-philosophy: behavior over implementation detail, the two acid tests, the Testing Trophy, and the e2e necessity floor. Stack-agnostic. Pass that skill's content into the Check 2, 3, and 4 briefs so they judge tests against one shared bar.
• Check 7 applies /security-audit (which itself layers on /wstg): the confidence gate, false-positive precedents, three-phase methodology, WSTG mapping, and dependency audit. Pass that skill's content into the Check 7 brief.

Step 1: Gather inputs (main agent)

Before spawning subagents, collect: