forge-workflow 1.3.1 → 1.4.0

package/.claude/commands/check.md

@@ -76,6 +76,14 @@ npm run test    # or: bun run test, jest, vitest, etc.
 - Includes security test scenarios
 - TDD tests from /dev phase
 
+> **💭 Plan-Act-Reflect Checkpoint**
+> Before declaring validation complete:
+> - Are all security test scenarios from your research doc actually implemented and passing?
+> - Did you verify OWASP Top 10 mitigations, not just check a box?
+> - Are there edge cases or integration scenarios you haven't tested?
+>
+> **If unsure**: Re-read the "Security Analysis" and "TDD Test Scenarios" sections in research doc
+
 ### Step 6: Handle Failures
 
 If any check fails:

package/.claude/commands/dev.md

@@ -39,6 +39,14 @@ CO-DEPENDENT (Must Sequence):
 Decision: Parallel tracks possible after types created
 ```
 
+> **💭 Plan-Act-Reflect Checkpoint**
+> Before choosing your execution strategy:
+> - Is the parallelization complexity worth the time savings?
+> - Do you have clear boundaries between tracks, or will they collide?
+> - Have you identified the true "shared foundation" that must come first?
+>
+> **If unsure**: Start sequential. Refer to your OpenSpec `tasks.md` for dependency guidance.
+
 ### Step 2: Create TodoWrite (TDD Pattern)
 
 **TESTS WRITTEN UPFRONT** - Before implementation

package/.claude/commands/plan.md

@@ -35,6 +35,14 @@ cat docs/research/<feature-slug>.md
 - Then create Beads issue
 - Multi-session or parallel work
 
+> **💭 Plan-Act-Reflect Checkpoint**
+> Before proceeding, reflect on this scope decision:
+> - Does this change affect system architecture, APIs, or data models?
+> - Will future features depend on getting this design right now?
+> - Would a team discussion reveal concerns or better alternatives?
+>
+> **If unsure**: Review your research doc (`docs/research/<feature-slug>.md`) for complexity signals
+
 ### Step 3A: If Tactical
 
 ```bash