+2 -2

src/db/session-store.ts

reviewed

··· 192 192 input.inputs ?? null, 193 193 input.outputs ?? null, 194 194 input.approach, 195 195 - input.testing ?? null, 195 195 + input.testing, 196 196 input.successCriteria, 197 197 null, // notes start empty 198 198 ); ··· 204 204 inputs: input.inputs ?? "", 205 205 outputs: input.outputs ?? "", 206 206 approach: input.approach, 207 207 - testing: input.testing ?? "", 207 207 + testing: input.testing, 208 208 successCriteria: input.successCriteria, 209 209 notes: "", 210 210 };

+13

src/prompts/bootstrap.ts

reviewed

··· 71 71 □ Inputs reference dependencies by description (e.g., "auth module from Authentication work") 72 72 □ Outputs are specific enough to search for later 73 73 74 74 + ## RICH DETAIL IN APPROACH 75 75 + 76 76 + The Approach section is freeform text. Include enough detail that you could execute the plan even after losing all conversation context. 77 77 + 78 78 + Consider including where appropriate: 79 79 + - **Code samples** when the implementation logic is non-obvious or critical to get right 80 80 + - **Directory/file structure** when creating new packages or reorganizing code 81 81 + - **Tables** when tracking multiple files to change or mapping old patterns to new ones 82 82 + - **Edge cases** when there are failure modes or boundary conditions to handle 83 83 + - **Data flow** when multiple components interact in a specific sequence 84 84 + 85 85 + The goal is self-contained executability: if you read ONLY the plan file, you should be able to implement it correctly. 86 86 + 74 87 ## TESTING IS REQUIRED 75 88 76 89 Every plan MUST include concrete testing instructions. Before completing a plan, you MUST run these tests.

+6 -2

src/tools/queue-add.ts

reviewed

··· 21 21 approach: z 22 22 .string() 23 23 .min(1, "Approach is required") 24 24 - .describe("How to accomplish the goal (detailed, actionable steps)"), 24 24 + .describe( 25 25 + "How to accomplish the goal. Include enough detail (steps, code samples, " + 26 26 + "structure, edge cases) that the plan is executable without additional context.", 27 27 + ), 25 28 success_criteria: z 26 29 .string() 27 30 .min(1, "Success criteria is required") ··· 30 33 .string() 31 34 .min(1, "Testing is required") 32 35 .describe( 33 33 - "How to verify the implementation works (commands to run, expected outputs)", 36 36 + "How to verify the implementation works. Include specific commands, " + 37 37 + "expected outputs, and edge cases to validate.", 34 38 ), 35 39 inputs: z 36 40 .string()

+1 -1

validation/scripts/invoke-inner.ps1

reviewed

··· 76 76 - Goal: Specific, measurable objective (at FEATURE level, not function level) 77 77 - Inputs: What this plan needs from other plans (by description) 78 78 - Outputs: What this plan produces that others may need 79 79 - - Approach: Concrete, actionable steps 79 79 + - Approach: Concrete, actionable steps. Include enough detail (code samples, structure, edge cases) that the plan is executable without additional context. 80 80 - Testing: REQUIRED! Specific commands to verify the implementation works (e.g., "Run npm run build - should compile without errors") 81 81 - Success Criteria: How you'll know it's done 82 82