maxsimcli 4.8.0 → 4.9.0

package/dist/assets/templates/workflows/settings.md

@@ -1,5 +1,5 @@
 <purpose>
-Interactive configuration of MAXSIM workflow agents (research, plan_checker, verifier) and model profile selection via multi-question prompt. Updates .planning/config.json with user preferences. Optionally saves settings as global defaults (~/.maxsim/defaults.json) for future projects.
+Interactive configuration of MAXSIM workflow agents (research, plan_checker, verifier) and model profile selection via multi-question prompt. Includes integrated profile management with detailed model assignment descriptions per tier. Updates .planning/config.json with user preferences. Optionally saves settings as global defaults (~/.maxsim/defaults.json) for future projects.
 </purpose>
 
 <required_reading>
@@ -30,9 +30,9 @@ cat .planning/config.json
 ```
 
 Parse current values (default to `true` if not present):
-- `workflow.research` — spawn researcher during plan-phase
-- `workflow.plan_checker` — spawn plan checker during plan-phase
-- `workflow.verifier` — spawn verifier during execute-phase
+- `workflow.research` — spawn researcher during /maxsim:plan
+- `workflow.plan_checker` — spawn plan checker during /maxsim:plan
+- `workflow.verifier` — spawn verifier during /maxsim:execute
 - `workflow.nyquist_validation` — validation architecture research during plan-phase
 - `model_profile` — which model each agent uses (default: `balanced`)
 - `git.branching_strategy` — branching approach (default: `"none"`)
@@ -45,12 +45,12 @@ Use AskUserQuestion with current values pre-selected:
 AskUserQuestion([
   {
     question: "Which model profile for agents?",
-    header: "Model",
+    header: "Model Profile",
     multiSelect: false,
     options: [
-      { label: "Quality", description: "Opus everywhere except verification (highest cost)" },
-      { label: "Balanced (Recommended)", description: "Opus for planning, Sonnet for execution/verification" },
-      { label: "Budget", description: "Sonnet for writing, Haiku for research/verification (lowest cost)" }
+      { label: "Quality", description: "Opus for planning/execution/debugging, Sonnet for verification. Best results, highest cost." },
+      { label: "Balanced (Recommended)", description: "Opus for planning, Sonnet for execution/verification. Good balance of quality and cost." },
+      { label: "Budget", description: "Sonnet for planning/execution, Haiku for research/verification. Lowest cost, good for rapid iteration." }
     ]
   },
   {
@@ -197,13 +197,17 @@ Display:
 | Git Branching        | {None/Per Phase/Per Milestone} |
 | Saved as Defaults    | {Yes/No} |
 
-These settings apply to future /maxsim:plan-phase and /maxsim:execute-phase runs.
+These settings apply to future /maxsim:plan and /maxsim:execute runs.
 
-Quick commands:
-- /maxsim:set-profile <profile> — switch model profile
-- /maxsim:plan-phase --research — force research
-- /maxsim:plan-phase --skip-research — skip research
-- /maxsim:plan-phase --skip-verify — skip plan check
+Profile Details ({quality/balanced/budget}):
+| Agent Role | Model |
+|------------|-------|
+| Planner | {model from MODEL_PROFILES} |
+| Executor | {model from MODEL_PROFILES} |
+| Researcher | {model from MODEL_PROFILES} |
+| Verifier | {model from MODEL_PROFILES} |
+
+Re-run /maxsim:settings anytime to change these.
 ```
 </step>
 

package/dist/assets/templates/workflows/verify-phase.md

@@ -1,6 +1,6 @@
 <sanity_check>
 Before executing any step in this workflow, verify:
-1. The current directory contains a `.planning/` folder — if not, stop and tell the user to run `/maxsim:new-project` first.
+1. The current directory contains a `.planning/` folder — if not, stop and tell the user to run `/maxsim:init` first.
 2. `.planning/ROADMAP.md` exists — if not, stop and tell the user to initialize the project.
 </sanity_check>
 

package/dist/assets/templates/workflows/verify-work.md

@@ -1,5 +1,5 @@
 <purpose>
-Validate built features through conversational testing with persistent state. Creates UAT.md that tracks test progress, survives /clear, and feeds gaps into /maxsim:plan-phase --gaps.
+Validate built features through conversational testing with persistent state. Creates UAT.md that tracks test progress, survives /clear, and feeds gaps into /maxsim:plan --gaps.
 
 User tests, Claude records. One test at a time. Plain text responses.
 </purpose>
@@ -73,7 +73,7 @@ If no, continue to `create_uat_file`.
 ```
 No active UAT sessions.
 
-Provide a phase number to start testing (e.g., /maxsim:verify-work 4)
+Provide a phase number to start testing (e.g., /maxsim:execute 4)
 ```
 
 **If no active sessions AND $ARGUMENTS provided:**
@@ -334,8 +334,8 @@ Present summary:
 ```
 All tests passed. Ready to continue.
 
-- `/maxsim:plan-phase {next}` — Plan next phase
-- `/maxsim:execute-phase {next}` — Execute next phase
+- `/maxsim:plan {next}` — Plan next phase
+- `/maxsim:execute {next}` — Execute next phase
 ```
 </step>
 
@@ -372,7 +372,7 @@ Display:
 ◆ Spawning planner for gap closure...
 ```
 
-Spawn maxsim-planner in --gaps mode:
+Spawn planner in --gaps mode:
 
 ```
 Task(
@@ -391,11 +391,11 @@ Task(
 </planning_context>
 
 <downstream_consumer>
-Output consumed by /maxsim:execute-phase
+Output consumed by /maxsim:execute
 Plans must be executable prompts.
 </downstream_consumer>
 """,
-  subagent_type="maxsim-planner",
+  subagent_type="planner",
   model="{planner_model}",
   description="Plan gap fixes for Phase {phase}"
 )
@@ -420,7 +420,7 @@ Display:
 
 Initialize: `iteration_count = 1`
 
-Spawn maxsim-plan-checker:
+Spawn plan checker (planner in verification mode):
 
 ```
 Task(
@@ -442,7 +442,7 @@ Return one of:
 - ## ISSUES FOUND — structured issue list
 </expected_output>
 """,
-  subagent_type="maxsim-plan-checker",
+  subagent_type="planner",
   model="{checker_model}",
   description="Verify Phase {phase} fix plans"
 )
@@ -460,7 +460,7 @@ On return:
 
 Display: `Sending back to planner for revision... (iteration {N}/3)`
 
-Spawn maxsim-planner with revision context:
+Spawn planner with revision context:
 
 ```
 Task(
@@ -484,7 +484,7 @@ Read existing PLAN.md files. Make targeted updates to address checker issues.
 Do NOT replan from scratch unless issues are fundamental.
 </instructions>
 """,
-  subagent_type="maxsim-planner",
+  subagent_type="planner",
   model="{planner_model}",
   description="Revise Phase {phase} plans"
 )
@@ -500,7 +500,7 @@ Display: `Max iterations reached. {N} issues remain.`
 Offer options:
 1. Force proceed (execute despite issues)
 2. Provide guidance (user gives direction, retry)
-3. Abandon (exit, user runs /maxsim:plan-phase manually)
+3. Abandon (exit, user runs /maxsim:plan manually)
 
 Wait for user response.
 </step>
@@ -528,7 +528,7 @@ Plans verified and ready for execution.
 
 **Execute fixes** — run fix plans
 
-`/clear` then `/maxsim:execute-phase {phase} --gaps-only`
+`/clear` then `/maxsim:execute {phase} --gaps-only`
 
 ───────────────────────────────────────────────────────────────
 ```
@@ -579,8 +579,8 @@ Default to **major** if unclear. User can correct if needed.
 - [ ] Batched writes: on issue, every 5 passes, or completion
 - [ ] Committed on completion
 - [ ] If issues: parallel debug agents diagnose root causes
-- [ ] If issues: maxsim-planner creates fix plans (gap_closure mode)
-- [ ] If issues: maxsim-plan-checker verifies fix plans
+- [ ] If issues: planner creates fix plans (gap_closure mode)
+- [ ] If issues: planner (in verification mode) verifies fix plans
 - [ ] If issues: revision loop until plans pass (max 3 iterations)
-- [ ] Ready for `/maxsim:execute-phase --gaps-only` when complete
+- [ ] Ready for `/maxsim:execute --gaps-only` when complete
 </success_criteria>