rpi-kit 2.2.2 → 2.4.0

package/commands/rpi/simplify.md

@@ -122,6 +122,17 @@ Output format:
 - Efficiency: {N} fixes
 - Lines removed: {N}
 - Lines added: {N}
+
+After simplification, append your activity to rpi/features/{slug}/ACTIVITY.md:
+
+### {current_date} — Razor (Simplify)
+- **Action:** Simplified implementation for {slug}
+- **Key decisions:** {for each <decision> tag you emitted: "summary (rationale)", separated by semicolons. If none: "No decisions in this phase."}
+- **Reuse fixes:** {count}
+- **Quality fixes:** {count}
+- **Efficiency fixes:** {count}
+- **Lines removed:** {count}
+- **Quality:** {your quality gate result}
 ```
 
 Store Razor's output as `$RAZOR_OUTPUT`.
@@ -176,7 +187,26 @@ Commit: {$SIMPLIFY_COMMIT}
 - Net lines: {+/-N}
 ```
 
-## Step 9: Output summary
+## Step 9: Consolidate decisions to DECISIONS.md
+
+1. Read `rpi/features/{slug}/ACTIVITY.md`.
+2. Extract all `<decision>` tags from entries belonging to the Simplify phase (Razor entries from this run).
+3. If no decisions found, skip this step.
+4. Read `rpi/features/{slug}/DECISIONS.md` if it exists (to get the last decision number for sequential numbering).
+5. Append a new section to `rpi/features/{slug}/DECISIONS.md`:
+
+```markdown
+## Simplify Phase
+_Generated: {current_date}_
+
+| # | Type | Decision | Alternatives | Rationale | Impact |
+|---|------|----------|-------------|-----------|--------|
+| {N} | {type} | {summary} | {alternatives} | {rationale} | {impact} |
+```
+
+6. Number decisions sequentially, continuing from the last number in DECISIONS.md.
+
+## Step 10: Output summary
 
 ```
 Simplify complete: {slug}

package/commands/rpi/status.md

@@ -61,6 +61,24 @@ For each feature:
 - Read `implement/IMPLEMENT.md` if it exists. Count completed tasks (`- [x]`) vs total.
 - Express as: `{completed}/{total} tasks`
 
+### Activity Log
+- Read `{feature_dir}/ACTIVITY.md` if it exists.
+- Extract the last 3 activity entries.
+- Extract quality scores from all entries — build a quality summary per phase:
+  - Research: {PASS|WEAK|FAIL|pending} (Atlas, Scout, Nexus scores)
+  - Plan: {PASS|WEAK|FAIL|pending} (Nexus interview, Mestre, Clara, adversarial scores)
+  - Implement: {PASS|WEAK|FAIL|pending} (Forge per-task scores)
+  - Simplify: {PASS|WEAK|FAIL|pending} (Razor score)
+  - Review: {PASS|WEAK|FAIL|pending} (Hawk, Shield, Sage, Nexus scores)
+  - Docs: {PASS|WEAK|FAIL|pending} (Quill score)
+- Identify any WEAK or FAIL scores for alerts.
+- Extract last activity timestamp for "last activity" display.
+
+### Decisions
+- Read `{feature_dir}/DECISIONS.md` if it exists.
+- Count total decisions, count by impact (HIGH, MEDIUM, LOW).
+- Extract the last 5 decisions (most recent = bottom of the file).
+
 ## Step 5: Display status
 
 ### If no specific feature requested (overview mode)
@@ -74,16 +92,38 @@ Output a status card per feature, sorted by phase (most advanced first):
 Phase: {phase} {task_progress if applicable}
 Verdict: {verdict}
 Complexity: {complexity}
+Last activity: {relative time, e.g. "2h ago" or "3 days ago"}
+Quality: {phase_quality_summary, e.g. "Research PASS | Plan PASS | Implement 3/7"}
+Decisions: {total} ({HIGH_count} HIGH, {MEDIUM_count} MEDIUM, {LOW_count} LOW)
 
 ## {feature-slug-2}
 Phase: {phase}
 Verdict: {verdict}
 Complexity: {complexity}
+Last activity: {relative time, e.g. "2h ago" or "3 days ago"}
+Quality: {phase_quality_summary, e.g. "Research PASS | Plan PASS | Implement 3/7"}
+Decisions: {total} ({HIGH_count} HIGH, {MEDIUM_count} MEDIUM, {LOW_count} LOW)
 
 ---
 {total_count} feature(s) active
 ```
 
+### Quality Alerts
+
+After the feature cards, if any feature has WEAK or FAIL quality scores:
+
+```
+## Alerts
+
+- {feature}: {phase} quality WEAK — {agent} ({reason from activity log})
+  Suggestion: {actionable suggestion, e.g. "Re-run /rpi:research" or "Add context to REQUEST.md"}
+
+- {feature}: {phase} quality FAIL — {agent} ({reason})
+  Suggestion: {actionable suggestion}
+```
+
+If no alerts: omit this section entirely.
+
 Phase display format:
 - `request` → "request (awaiting research)"
 - `research` → "research (awaiting plan)"
@@ -112,6 +152,7 @@ Complexity: {complexity}
 - plan/pm.md: {exists/missing}
 - plan/ux.md: {exists/missing}
 - implement/IMPLEMENT.md: {exists/missing}
+- DECISIONS.md: {exists/missing}
 - delta/: {count of files in ADDED + MODIFIED + REMOVED}
 
 ## Tasks
@@ -122,6 +163,34 @@ Complexity: {complexity}
 
 ## Next
 {Suggest the next command to run, e.g. "/rpi {slug}" or "/rpi:archive {slug}" if complete}
+
+## Activity Log (last 5 entries)
+{If ACTIVITY.md exists, show last 5 entries in reverse chronological order}
+{If no ACTIVITY.md: "No activity log yet."}
+
+## Key Decisions (last 5)
+{If DECISIONS.md exists:}
+| # | Phase | Decision | Impact |
+|---|-------|----------|--------|
+| {N} | {phase} | {summary} | {impact} |
+
+Total: {N} decisions ({HIGH_count} HIGH, {MEDIUM_count} MEDIUM, {LOW_count} LOW)
+Full log: rpi/features/{slug}/DECISIONS.md
+
+{If no DECISIONS.md: "No decisions logged yet."}
+
+## Quality Summary
+{For each completed phase, show quality scores:}
+- Research: Atlas {score} | Scout {score} | Nexus {score}
+- Plan: Interview {score} | Mestre {score} | Clara {score} | Adversarial {score}
+- Implement: {N}/{total} tasks, Forge avg quality {score}
+- Simplify: Razor {score}
+- Review: Hawk {score} | Shield {score} | Sage {score}
+- Docs: Quill {score}
+
+## Session Resume
+Last activity: {timestamp and description of last logged action}
+Next step: {suggest the next command based on current phase}
 ```
 
 If the requested feature does not exist:

package/marketplace.json

@@ -5,14 +5,14 @@
   },
   "metadata": {
     "description": "Research → Plan → Implement. 7-phase pipeline with 13 named agents, delta specs, party mode, and knowledge compounding.",
-    "version": "2.2.2"
+    "version": "2.4.0"
   },
   "plugins": [
     {
       "name": "rpi-kit",
       "source": "./",
       "description": "Research → Plan → Implement. 7-phase pipeline with 13 named agents, delta specs, party mode, and knowledge compounding.",
-      "version": "2.2.2",
+      "version": "2.4.0",
       "author": {
         "name": "Daniel Mendes"
       },
@@ -24,6 +24,7 @@
         "./commands/rpi/docs.md",
         "./commands/rpi/docs-gen.md",
         "./commands/rpi/evolve.md",
+        "./commands/rpi/fix.md",
         "./commands/rpi/implement.md",
         "./commands/rpi/init.md",
         "./commands/rpi/learn.md",

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "rpi-kit",
-  "version": "2.2.2",
+  "version": "2.4.0",
   "description": "Research → Plan → Implement. AI-assisted feature development with 13 named agents, delta specs, and knowledge compounding.",
   "license": "MIT",
   "author": "Daniel Mendes",