maestro-flow 0.3.12 → 0.3.14

package/.codex/skills/maestro-brainstorm/SKILL.md

@@ -60,7 +60,7 @@ Wave-based multi-role brainstorming using `spawn_agents_on_csv`. Diamond topolog
 $maestro-brainstorm "Build real-time collaboration platform"
 $maestro-brainstorm -y "Build real-time collaboration platform"
 $maestro-brainstorm -c 6 "Build real-time collaboration platform --count 5"
-$maestro-brainstorm --continue "brainstorm-collab-20260318"
+$maestro-brainstorm --continue "20260318-brainstorm-collab"
 ```
 
 **Flags**:
@@ -125,7 +125,7 @@ Each wave generates `wave-{N}.csv` with extra `prev_context` column.
 ### Session Structure
 
 ```
-.workflow/.csv-wave/brainstorm-{slug}-{date}/
+.workflow/.csv-wave/{YYYYMMDD}-brainstorm-{slug}/
 +-- tasks.csv
 +-- results.csv
 +-- discoveries.ndjson
@@ -184,7 +184,7 @@ const topicArg = $ARGUMENTS
 
 const slug = topicArg.toLowerCase().replace(/[^a-z0-9]+/g, '-').substring(0, 40)
 const dateStr = getUtc8ISOString().substring(0, 10).replace(/-/g, '')
-const sessionId = `brainstorm-${slug}-${dateStr}`
+const sessionId = `${dateStr}-brainstorm-${slug}`
 const sessionFolder = `.workflow/.csv-wave/${sessionId}`
 
 Bash(`mkdir -p ${sessionFolder}/.brainstorming`)
@@ -196,7 +196,7 @@ Bash(`mkdir -p ${sessionFolder}/.brainstorming`)
 
 **Decomposition Rules**:
 
-1. **Mode detection**: Number = phase mode (resolve via state.json artifact registry to `.workflow/scratch/{type}-{slug}-{date}/`; legacy fallback to `.workflow/phases/{NN}-{slug}/`), text = scratch mode
+1. **Mode detection**: Number = phase mode (resolve via state.json artifact registry to `.workflow/scratch/{YYYYMMDD}-{type}-{slug}/`), text = scratch mode
 2. **Project specs loading**: Read `.workflow/specs/` for architecture-aware analysis context
 3. **Role selection**:
 

package/.codex/skills/maestro-coordinate/SKILL.md

@@ -106,7 +106,7 @@ const AUTO_FLAG_MAP = {
 
 function assembleArgs(step) {
   let a = (step.args || '')
-    .replace(/\{phase\}/g, context.current_phase || '')
+    .replace(/\{phase\}/g, context.phase || '')
     .replace(/\{description\}/g, context.user_intent || '')
     .replace(/\{issue_id\}/g, context.issue_id || '')
     .replace(/\{spec_session_id\}/g, context.spec_session_id || '')
@@ -145,7 +145,7 @@ Bash({
 ```javascript
 // Context propagation from output
 const phaseMatch = output.match(/PHASE:\s*(\d+)/m);
-if (phaseMatch) context.current_phase = phaseMatch[1];
+if (phaseMatch) context.phase = phaseMatch[1];  // derived from output, not stored in state
 const specMatch = output.match(/SPEC-[\w-]+/);
 if (specMatch) context.spec_session_id = specMatch[0];
 const scratchMatch = output.match(/scratch_dir:\s*(.+)/m);

package/.codex/skills/maestro-execute/SKILL.md

@@ -60,7 +60,7 @@ $maestro-execute "3"
 $maestro-execute -c 4 "3 --auto-commit"
 $maestro-execute -y "3 --method cli"
 $maestro-execute "3 --dir .workflow/scratch/quick-fix"
-$maestro-execute --continue "execute-phase3-20260318"
+$maestro-execute --continue "20260318-execute-P3-phase3"
 ```
 
 **Flags**:
@@ -130,7 +130,7 @@ Each wave generates `wave-{N}.csv` with extra `prev_context` column populated fr
 ### Session Structure
 
 ```
-.workflow/.csv-wave/execute-{phase}-{date}/
+.workflow/.csv-wave/{YYYYMMDD}-execute-P{N}-{slug}/
 +-- tasks.csv
 +-- results.csv
 +-- discoveries.ndjson
@@ -181,8 +181,8 @@ const phaseArg = $ARGUMENTS
 
 const dateStr = getUtc8ISOString().substring(0, 10).replace(/-/g, '')
 const sessionId = scratchDir
-  ? `execute-scratch-${dateStr}`
-  : `execute-phase${phaseArg}-${dateStr}`
+  ? `${dateStr}-execute-scratch`
+  : `${dateStr}-execute-P${phaseArg}-${phaseSlug}`
 const sessionFolder = `.workflow/.csv-wave/${sessionId}`
 
 Bash(`mkdir -p ${sessionFolder}`)
@@ -325,9 +325,19 @@ If a task is blocked/failed and other tasks in later waves depend on it:
 5. **Extract incremental learnings**:
    - Read all `.summaries/` from PLAN_DIR
    - Extract strategy adjustments, patterns, pitfalls
-   - Append to `.workflow/specs/learnings.md`
+   - Check existing entries via `maestro spec load --category learning` (dedup)
+   - Append to `.workflow/specs/learnings.md` using `<spec-entry>` closed-tag format (category=`learning`, auto-extract keywords, date=today, source=`execute`)
    - Mark artifact `harvested: true` in state.json
 
+5b. **Post-task Knowledge Inquiry** (after each task completes):
+   - **Execution deviation**: If task summary mentions approach change, dependency swap, or plan deviation:
+     → Ask: "TASK-{NNN} deviated from the plan. Should this decision be recorded as an architecture constraint? (`/spec-add arch`)"
+   - **Retry success**: If task required ≥2 retries before completion:
+     → Ask: "TASK-{NNN} succeeded after {N} retries. Should this fix pattern be documented? (`/spec-add debug`)"
+   - **Implicit knowledge**: If task summary contains design rationale ("chose X because", "rejected Y due to"):
+     → Ask: "Design decision detected. Should it be recorded as a learning? (`/spec-add learning`)"
+   - If user confirms, append `<spec-entry>` to matching category file via `spec-add` mechanism
+
 6. **Generate context.md**:
 
 ```markdown

package/.codex/skills/maestro-init/SKILL.md

@@ -16,7 +16,7 @@ When `--auto`: After config questions, run research without further interaction.
 ```bash
 $maestro-init ""
 $maestro-init "--auto"
-$maestro-init "--from-brainstorm brainstorm-auth-20260318"
+$maestro-init "--from-brainstorm 20260318-brainstorm-auth"
 ```
 
 **Flags**: