feat: agent quality improvements (#120, #121, #124)#154
Merged
Conversation
Simplifier: replace vague clarity bullets with 8 structured slop detection categories (language-behavior tests, redundant type checks, over-defensive handling, debug remnants, commented-out code, unused imports, verbose names, unnecessary intermediates). Scrutinizer: add stub detection responsibility between P0 and P1 evaluation, backed by new stub-detection.md reference covering component stubs, API/service stubs, hook/effect stubs, and wiring gaps. Shepherd: add goal-backward verification (trace from user goals to implementation), artifact depth table (Exists/Substantive/Wired), stub misalignment type, and re-verification section for retry runs.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
stub-detection.mdreference file covering component stubs, API/service stubs, hook/effect stubs, and wiring gaps (flagged as P0-Functionality)stubmisalignment type, re-verification section for retry runsPrompt-only enhancements to existing agents — no new infrastructure, commands, or plugins. Foundation for #115 (Continuous Learning).
Key files
shared/agents/simplifier.mdshared/agents/scrutinizer.mdshared/agents/shepherd.mdshared/skills/self-review/references/stub-detection.mdCHANGELOG.mdTest plan
npm run build— all 35 skills, 10 agents distributed across 17 pluginsnpm test— 273/273 tests pass, no regressionsplugins/devflow-*/agents/match sourcestub-detection.mdexists inplugins/devflow-self-review/skills/self-review/references/Closes #120, closes #121, closes #124