Cursor rule

1---
2description: "Run Mock User and Auditor agents against a feature in fresh contexts before human review. Use after verify-work, before request-review, when user wants pre-review simulation."
3alwaysApply: false
4---
5 
6# Simulate Agents
7> **HARD GATE** — **HARD GATE** — Simulations are hypothetical. Do NOT use sim results to make production decisions without validation on real agents. Sims help discover gaps, not replace testing.
8 
9 
10Two roles, **isolated contexts** (no shared state with BUILD agent):
11 
121. **Mock User** — follows Verification Script; reports UX gaps in plain language.
132. **Auditor** — checks CONVENTIONS.md, security checklist, test coverage; structured pass/fail.
14 
15## Process
16 
171. Read story Verification Script + changed files diff.
182. Spawn Mock User: step through UAT script; log failures.
193. Spawn Auditor: run `audit-code` checklist cold.
204. Write `specs/SIMULATION-<feature>.md` with both reports.
215. Failed items → `respond-review` or `plan-work` gaps — do not skip human review.
22 
23## Verify
24 
25→ verify: `test -f skills/simulate-agents/SKILL.md && test -d specs/verifications`
26