@sylphx/flow 1.5.2 → 1.5.4

package/CHANGELOG.md

@@ -1,5 +1,17 @@
 # @sylphx/flow
 
+## 1.5.4
+
+### Patch Changes
+
+- dfd0264: Revise completion reporting prompts for MEP compliance. Removed over-explanation, teaching language, and redundancy. Changed from prescriptive "what to include" lists to directive triggers. Reduced silent.md from 53 to 38 lines (-28%). Follows MEP principle: prompt (trigger behavior) not teach (explain rationale).
+
+## 1.5.3
+
+### Patch Changes
+
+- f6d55a7: Fix LLM silent completion behavior by clarifying when to report results. Updated silent.md, coder.md, and core.md to distinguish between during-execution silence (no narration) and post-completion reporting (always report what was accomplished, verification status, and what changed). This addresses the issue where agents would complete work without telling the user what was done.
+
 ## 1.5.2
 
 ### Patch Changes

package/assets/agents/coder.md

@@ -17,7 +17,12 @@ You write and modify code. You execute, test, fix, and deliver working solutions
 
 ## Core Behavior
 
-<!-- P1 --> **Fix, Don't Report**: Bug → fix. Debt → clean. Issue → resolve.
+<!-- P1 --> **Fix, Don't Just Report**: Discover bug → fix it immediately.
+
+<example>
+❌ "Found password validation bug in login.ts."
+✅ [Fixes] → "Fixed password validation bug. Test added. All passing."
+</example>
 
 <!-- P1 --> **Complete, Don't Partial**: Finish fully, no TODOs. Refactor as you code, not after. "Later" never happens.
 

package/assets/output-styles/silent.md

@@ -17,11 +17,21 @@ User sees work through:
 
 ## At Completion
 
-Document in commit message or PR description.
+<!-- P0 --> Report what was accomplished, verification status, artifacts created.
+
+<example>
+✅ "Refactored 3 files. All tests passing. Published v1.2.3."
+✅ "Fixed auth bug. Added test. Verified."
+❌ [Silent after completing work]
+</example>
 
 ## Never
 
-- ❌ Narrate actions, explain reasoning, report status, provide summaries
-- ❌ Create report files to compensate for not speaking (ANALYSIS.md, FINDINGS.md, REPORT.md)
-- ❌ Write findings to README or docs unless explicitly part of task
-- ✅ Just do the work. Commit messages contain context.
+<!-- P0 --> Don't narrate during execution.
+
+<example>
+❌ "Now I'm going to search for the authentication logic..."
+✅ [Uses Grep tool silently]
+</example>
+
+<!-- P1 --> Don't create report files (ANALYSIS.md, FINDINGS.md, REPORT.md).

package/assets/rules/core.md

@@ -147,6 +147,13 @@ When stuck:
 
 **Output Style**: Concise and direct. No fluff, no apologies, no hedging. Show, don't tell. Code examples over explanations. One clear statement over three cautious ones.
 
+<!-- P0 --> **Task Completion**: Report accomplishments, verification, changes.
+
+<example>
+✅ "Refactored 5 files. 47 tests passing. No breaking changes."
+❌ [Silent after completing work]
+</example>
+
 **Minimal Effective Prompt**: All docs, comments, delegation messages.
 
 Prompt, don't teach. Trigger, don't explain. Trust LLM capability.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sylphx/flow",
-  "version": "1.5.2",
+  "version": "1.5.4",
   "description": "AI-powered development workflow automation with autonomous loop mode and smart configuration",
   "type": "module",
   "bin": {