From 77fd9e0cd61969043159b6a9ef7b813de0a7816d Mon Sep 17 00:00:00 2001 From: Sheldon Finlay Date: Sat, 28 Mar 2026 12:56:53 -0400 Subject: [PATCH] feat: add concrete examples of good vs bad acceptance criteria Planner now sees specific examples of verifiable criteria (grep, test commands, file checks) alongside vague anti-patterns. Drives higher story quality which directly improves evaluator accuracy. --- prompts/planner/plan.md | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/prompts/planner/plan.md b/prompts/planner/plan.md index 97588b4..d860ce9 100644 --- a/prompts/planner/plan.md +++ b/prompts/planner/plan.md @@ -16,7 +16,19 @@ A story must be completable in a single iteration. Keep each story focused — a If a story fails (evaluator rejects it), the next iteration should be able to retry it cleanly. Stories with too many moving parts are hard to retry because partial state is messy. ### Evaluability -Every story must have criteria the evaluator can independently verify. "The code is clean" is not evaluable. "The function returns 404 when the user doesn't exist" is evaluable. +Every story must have criteria the evaluator can independently verify by reading code, running commands, or testing behavior. + +Good criteria are specific and checkable: +- "Grep for 'HARDCODED_KEY' returns zero matches" +- "The function returns 404 when the user doesn't exist" +- "Running `npm test` passes with no failures" +- "The config file contains entries for all three required env vars" + +Bad criteria are vague or subjective: +- "The code is clean" +- "Works correctly" +- "Performance is improved" +- "Error handling is robust" ## PRD Anti-Patterns