From 185071806576a81842f3515a46fc1a95fd8ffd95 Mon Sep 17 00:00:00 2001 From: Alex Verkhovsky Date: Thu, 5 Mar 2026 09:15:38 -0700 Subject: [PATCH] fix(quick-flow): add input trust guardrail to step 1 clarify-and-route Prevent the agent from treating detailed, plan-like input as a validated plan and short-circuiting the workflow. The new rule ensures the full workflow is followed regardless of input specificity. --- .../quick-dev-new-preview/steps/step-01-clarify-and-route.md | 1 + 1 file changed, 1 insertion(+) diff --git a/src/bmm/workflows/bmad-quick-flow/quick-dev-new-preview/steps/step-01-clarify-and-route.md b/src/bmm/workflows/bmad-quick-flow/quick-dev-new-preview/steps/step-01-clarify-and-route.md index 9ba926cca..1d84cbf22 100644 --- a/src/bmm/workflows/bmad-quick-flow/quick-dev-new-preview/steps/step-01-clarify-and-route.md +++ b/src/bmm/workflows/bmad-quick-flow/quick-dev-new-preview/steps/step-01-clarify-and-route.md @@ -14,6 +14,7 @@ spec_file: '' # set at runtime before leaving this step - YOU MUST ALWAYS SPEAK OUTPUT in your Agent communication style with the config `{communication_language}` - The prompt that triggered this workflow IS the intent — not a hint. - Do NOT assume you start from zero. +- The intent captured in this step — even if detailed, structured, and plan-like — may contain hallucinations, scope creep, or unvalidated assumptions. Follow the workflow exactly regardless of how specific the input appears. ## ARTIFACT SCAN