@automagik/genie 0.260203.629 → 0.260203.711

package/plugins/automagik-genie/skills/council/SKILL.md

@@ -0,0 +1,80 @@
+---
+name: council
+description: "Multi-perspective brainstorming and critique with 10 specialized council members. Use during architecture decisions, wish planning, or reviews to get diverse viewpoints."
+---
+
+# /council - Multi-Perspective Review
+
+Use the council (a crew of specialist subagents) to brainstorm, critique, or vote.
+
+## When to Use
+
+- During `/wish`: Generate 2-3 approaches with tradeoffs
+- During `/review`: Find risks and gaps
+- During architecture decisions: Get independent perspectives
+- When stuck: Fresh viewpoints break deadlocks
+
+## Council Members
+
+| Member | Focus | Philosophy |
+|--------|-------|------------|
+| **questioner** | Challenge assumptions | "Why? Is there a simpler way?" |
+| **benchmarker** | Performance evidence | "Show me the benchmarks." |
+| **simplifier** | Complexity reduction | "Delete code. Ship features." |
+| **sentinel** | Security oversight | "Where are the secrets? What's the blast radius?" |
+| **ergonomist** | Developer experience | "If you need to read the docs, the API failed." |
+| **architect** | Systems thinking | "Talk is cheap. Show me the code." |
+| **operator** | Operations reality | "No one wants to run your code." |
+| **deployer** | Zero-config deployment | "Zero-config with infinite scale." |
+| **measurer** | Observability | "Measure, don't guess." |
+| **tracer** | Production debugging | "You will debug this in production." |
+
+## Smart Routing
+
+Not every decision needs all 10 perspectives:
+
+| Topic | Members |
+|-------|---------|
+| Architecture | questioner, benchmarker, simplifier, architect |
+| Performance | benchmarker, questioner, architect, measurer |
+| Security | questioner, simplifier, sentinel |
+| API Design | questioner, simplifier, ergonomist, deployer |
+| Operations | operator, tracer, measurer |
+| Full Review | all 10 |
+
+**Default:** Core trio (questioner, benchmarker, simplifier)
+
+## Output Format
+
+```markdown
+## Council Advisory
+
+### Topic: [Detected Topic]
+### Members Consulted: [List]
+
+### Perspectives
+
+**questioner:**
+- [Key point]
+- Vote: [APPROVE/REJECT/MODIFY]
+
+**simplifier:**
+- [Key point]
+- Vote: [APPROVE/REJECT/MODIFY]
+
+...
+
+### Vote Summary
+- Approve: X
+- Reject: X
+- Modify: X
+
+### Synthesized Recommendation
+[Council's collective advisory]
+```
+
+## Philosophy
+
+**The council advises, the user decides.**
+
+Value is in diverse perspective, not gatekeeping. Each member surfaces blind spots and challenges assumptions.

package/plugins/automagik-genie/skills/{forge → make}/SKILL.md

@@ -1,9 +1,9 @@
 ---
-name: forge
+name: make
 description: "Use when executing an approved wish plan - dispatches implementor subagents per task with two-stage review (spec + quality) and fix loops."
 ---
 
-# Forge - Execute the Plan
+# Make - Execute the Plan
 
 ## Overview
 
@@ -114,7 +114,7 @@ Return to step 2 until all tasks are complete.
 
 ```
 All tasks complete.
-Output: "All forge tasks complete. Run /review for final validation."
+Output: "All make tasks complete. Run /review for final validation."
 ```
 
 ---

package/plugins/automagik-genie/skills/plan-review/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: plan-review
-description: "Validate a wish document (structure, scope boundaries, acceptance criteria, validation commands). Use after creating or editing .genie/wishes/<slug>/wish.md to catch missing sections before forge."
+description: "Validate a wish document (structure, scope boundaries, acceptance criteria, validation commands). Use after creating or editing .genie/wishes/<slug>/wish.md to catch missing sections before make."
 ---
 
 # Plan Review - Validate Wish Documents
@@ -61,7 +61,7 @@ Fast structural/quality check on wish documents before execution. Catches missin
 ```
 Plan review: PASS
 
-Wish document is well-structured and ready for /forge.
+Wish document is well-structured and ready for /make.
 ```
 
 **If checks fail:**

package/plugins/automagik-genie/skills/review/SKILL.md

@@ -1,13 +1,13 @@
 ---
 name: review
-description: "Use when all forge tasks are complete and work needs final validation - produces SHIP/FIX-FIRST/BLOCKED verdict with categorized gaps."
+description: "Use when all make tasks are complete and work needs final validation - produces SHIP/FIX-FIRST/BLOCKED verdict with categorized gaps."
 ---
 
 # Review - Final Validation
 
 ## Overview
 
-After forge completes all tasks, run comprehensive final review. Check every success criterion with evidence, run validation commands, do quality spot-check, and produce the ship decision.
+After make completes all tasks, run comprehensive final review. Check every success criterion with evidence, run validation commands, do quality spot-check, and produce the ship decision.
 
 **Three verdicts: SHIP / FIX-FIRST / BLOCKED**
 
@@ -23,14 +23,14 @@ Check TaskList for wish tasks
 Verify all tasks marked complete
 ```
 
-**If tasks incomplete:** Stop. Output: "Forge not complete. [N] tasks remaining. Run /forge to continue."
+**If tasks incomplete:** Stop. Output: "Make not complete. [N] tasks remaining. Run /make to continue."
 
 ### 2. Task Completion Audit
 
 For each execution group in the wish:
 - Check the task was completed
 - Verify acceptance criteria checkboxes are checked
-- Note any tasks that were BLOCKED during forge
+- Note any tasks that were BLOCKED during make
 
 **Output per group:**
 ```
@@ -108,14 +108,14 @@ Conditions:
   - MEDIUM/LOW gaps are advisory only
 ```
 
-**FIX-FIRST** - Fixable issues found. Return to forge.
+**FIX-FIRST** - Fixable issues found. Return to make.
 
 ```
 Conditions:
   - One or more HIGH gaps (fixable)
   - Or validation commands failing
   - Quality spot-check found significant concerns
-  - Provide specific fix list for /forge
+  - Provide specific fix list for /make
 ```
 
 **BLOCKED** - Fundamental issues. Return to wish.
@@ -123,8 +123,8 @@ Conditions:
 ```
 Conditions:
   - CRITICAL gaps that require scope changes
-  - Or architectural problems that can't be fixed in forge
-  - Any BLOCKED tasks from forge
+  - Or architectural problems that can't be fixed in make
+  - Any BLOCKED tasks from make
   - Provide specific issues requiring wish revision
 ```
 
@@ -181,7 +181,7 @@ Notes: [brief notes if any]
 
 **If FIX-FIRST:**
 ```
-"Review found fixable issues. Run /forge to address:
+"Review found fixable issues. Run /make to address:
 1. [gap 1]
 2. [gap 2]
 Then run /review again."
@@ -193,7 +193,7 @@ Then run /review again."
 Revise the wish document to address:
 1. [issue 1]
 2. [issue 2]
-Then run /forge and /review again."
+Then run /make and /review again."
 ```
 
 ---
@@ -214,8 +214,8 @@ Then run /forge and /review again."
 - Declare SHIP with CRITICAL or HIGH gaps
 - Skip validation commands
 - Mark criteria PASS without evidence
-- Re-implement fixes during review (that's forge's job)
+- Re-implement fixes during review (that's make's job)
 - Change scope during review (that's wish's job)
 - Block on MEDIUM or LOW gaps
-- Pass with BLOCKED tasks from forge
-- Forget to write results back to the wish document
+- Pass with BLOCKED tasks from make
+- Maket to write results back to the wish document

package/plugins/automagik-genie/skills/wish/SKILL.md

@@ -9,7 +9,7 @@ description: "Use when starting non-trivial work that needs structured planning
 
 Convert a validated design (from `/brainstorm`) or direct request into a structured wish document. Create native Claude Code tasks for execution.
 
-**Output:** `.genie/wishes/<slug>/wish.md` + native tasks ready for `/forge`
+**Output:** `.genie/wishes/<slug>/wish.md` + native tasks ready for `/make`
 
 ---
 
@@ -82,7 +82,7 @@ After writing the wish document:
 
 ### Phase 6: Handoff
 
-Output: **"Wish documented. Run `/plan-review` to validate, then `/forge` to begin execution."**
+Output: **"Wish documented. Run `/plan-review` to validate, then `/make` to begin execution."**
 
 ---
 

package/src/lib/log-reader.ts

@@ -67,18 +67,21 @@ export async function readSessionLogs(
     throw new Error(`Session "${sessionName}" not found`);
   }
 
-  // Get first window and pane
+  // Get active window and pane (never assume index 0)
   const windows = await tmux.listWindows(session.id);
   if (!windows || windows.length === 0) {
     throw new Error(`No windows found in session "${sessionName}"`);
   }
 
-  const panes = await tmux.listPanes(windows[0].id);
+  const activeWindow = windows.find(w => w.active) || windows[0];
+
+  const panes = await tmux.listPanes(activeWindow.id);
   if (!panes || panes.length === 0) {
     throw new Error(`No panes found in session "${sessionName}"`);
   }
 
-  const paneId = panes[0].id;
+  const activePane = panes.find(p => p.active) || panes[0];
+  const paneId = activePane.id;
 
   // Parse range if provided
   if (options.range) {
@@ -162,12 +165,15 @@ export async function followSessionLogs(
     throw new Error(`No windows found in session "${sessionName}"`);
   }
 
-  const panes = await tmux.listPanes(windows[0].id);
+  const activeWindow = windows.find(w => w.active) || windows[0];
+
+  const panes = await tmux.listPanes(activeWindow.id);
   if (!panes || panes.length === 0) {
     throw new Error(`No panes found in session "${sessionName}"`);
   }
 
-  const paneId = panes[0].id;
+  const activePane = panes.find(p => p.active) || panes[0];
+  const paneId = activePane.id;
   let lastContent = '';
   let following = true;
 

package/src/lib/orchestrator/event-monitor.ts

@@ -81,12 +81,15 @@ export class EventMonitor extends EventEmitter {
         throw new Error(`No windows found in session "${this.sessionName}"`);
       }
 
-      const panes = await tmux.listPanes(windows[0].id);
+      const activeWindow = windows.find(w => w.active) || windows[0];
+
+      const panes = await tmux.listPanes(activeWindow.id);
       if (!panes || panes.length === 0) {
         throw new Error(`No panes found in session "${this.sessionName}"`);
       }
 
-      this.paneId = panes[0].id;
+      const activePane = panes.find(p => p.active) || panes[0];
+      this.paneId = activePane.id;
     }
 
     this.running = true;

package/src/lib/version.ts

@@ -1,5 +1,5 @@
 // Runtime version (baked in at build time)
-export const VERSION = '0.260203.0629';
+export const VERSION = '0.260203.0711';
 
 // Generate version string from current datetime
 // Format: 0.YYMMDD.HHMM (e.g., 0.260201.1430 = Feb 1, 2026 at 14:30)