maxsimcli 5.0.2 → 5.0.3

package/dist/assets/CHANGELOG.md

@@ -1,3 +1,11 @@
+## [5.0.2](https://github.com/maystudios/maxsimcli/compare/v5.0.1...v5.0.2) (2026-03-12)
+
+
+### Bug Fixes
+
+* **github-ssot:** complete migration to GitHub Issues as sole source of truth ([2bf86bf](https://github.com/maystudios/maxsimcli/commit/2bf86bf6065048e859a2b760b2c4a04209c6da87))
+* **todos:** remove local file system — GitHub Issues is sole source of truth ([de98df1](https://github.com/maystudios/maxsimcli/commit/de98df18f88040b58cea32d576907a889151e9f9))
+
 ## [5.0.1](https://github.com/maystudios/maxsimcli/compare/v5.0.0...v5.0.1) (2026-03-12)
 
 

package/dist/assets/templates/agents/executor.md

@@ -11,7 +11,7 @@ skills:
   - evidence-collection
   - commit-conventions
 available_skills:
-  | github-artifact-protocol | .skills/github-artifact-protocol/SKILL.md | When reading from or writing to GitHub Issues |
+  | github-artifact-protocol | ~/.claude/skills/github-artifact-protocol/SKILL.md | When reading from or writing to GitHub Issues |
 ---
 
 You are a plan executor. You implement plans atomically -- one commit per task, deviations handled inline, every completion claim backed by tool output.

package/dist/assets/templates/agents/planner.md

@@ -10,7 +10,7 @@ skills:
   - handoff-contract
   - input-validation
 available_skills:
-  | github-artifact-protocol | .skills/github-artifact-protocol/SKILL.md | When reading from or writing to GitHub Issues |
+  | github-artifact-protocol | ~/.claude/skills/github-artifact-protocol/SKILL.md | When reading from or writing to GitHub Issues |
 ---
 
 You are a plan creator. You produce phase plans with frontmatter, task breakdown, dependency graphs, wave ordering, and must_haves verification criteria.

package/dist/assets/templates/agents/verifier.md

@@ -12,7 +12,7 @@ skills:
   - evidence-collection
   - handoff-contract
 available_skills:
-  | github-artifact-protocol | .skills/github-artifact-protocol/SKILL.md | When reading from or writing to GitHub Issues |
+  | github-artifact-protocol | ~/.claude/skills/github-artifact-protocol/SKILL.md | When reading from or writing to GitHub Issues |
 ---
 
 You are a verifier. You check work against specifications using fresh tool output as evidence. You NEVER trust prior claims -- you gather your own evidence for every criterion.

package/dist/assets/templates/commands/maxsim/execute.md

@@ -29,8 +29,8 @@ Execute the phase state machine: Execute all plans in wave order, auto-verify, r
 </objective>
 
 <execution_context>
-@./workflows/execute.md
-@./references/ui-brand.md
+@~/.claude/maxsim/workflows/execute.md
+@~/.claude/maxsim/references/ui-brand.md
 </execution_context>
 
 <context>
@@ -40,6 +40,6 @@ Context files are resolved inside the workflow via `maxsim-tools init execute-ph
 </context>
 
 <process>
-Execute the execute workflow from @./workflows/execute.md end-to-end.
+Execute the execute workflow from @~/.claude/maxsim/workflows/execute.md end-to-end.
 Preserve all workflow gates (state detection, wave execution, verification, retry loop, re-entry flow).
 </process>

package/dist/assets/templates/commands/maxsim/go.md

@@ -21,9 +21,9 @@ Show + Act pattern: display detection reasoning, then act. No arguments -- pure
 </objective>
 
 <execution_context>
-@./workflows/go.md
+@~/.claude/maxsim/workflows/go.md
 </execution_context>
 
 <process>
-Execute the go workflow from @./workflows/go.md end-to-end.
+Execute the go workflow from @~/.claude/maxsim/workflows/go.md end-to-end.
 </process>

package/dist/assets/templates/commands/maxsim/help.md

@@ -13,10 +13,10 @@ Output ONLY the reference content below. Do NOT add:
 </objective>
 
 <execution_context>
-@./workflows/help.md
+@~/.claude/maxsim/workflows/help.md
 </execution_context>
 
 <process>
-Output the complete MAXSIM command reference from @./workflows/help.md.
+Output the complete MAXSIM command reference from @~/.claude/maxsim/workflows/help.md.
 Display directly -- no additions or modifications.
 </process>

package/dist/assets/templates/commands/maxsim/init.md

@@ -38,15 +38,15 @@ Unified project initialization. Detects whether this is a new project, existing
 </objective>
 
 <execution_context>
-@./workflows/init.md
-@./references/questioning.md
-@./references/thinking-partner.md
-@./references/ui-brand.md
-@./templates/project.md
-@./templates/requirements.md
+@~/.claude/maxsim/workflows/init.md
+@~/.claude/maxsim/references/questioning.md
+@~/.claude/maxsim/references/thinking-partner.md
+@~/.claude/maxsim/references/ui-brand.md
+@~/.claude/maxsim/templates/project.md
+@~/.claude/maxsim/templates/requirements.md
 </execution_context>
 
 <process>
-Execute the init workflow from @./workflows/init.md end-to-end.
+Execute the init workflow from @~/.claude/maxsim/workflows/init.md end-to-end.
 Pass $ARGUMENTS through to the workflow for flag handling (--auto).
 </process>

package/dist/assets/templates/commands/maxsim/plan.md

@@ -30,8 +30,8 @@ Execute the plan state machine: Discussion -> Research -> Planning. Each stage p
 </objective>
 
 <execution_context>
-@./workflows/plan.md
-@./references/ui-brand.md
+@~/.claude/maxsim/workflows/plan.md
+@~/.claude/maxsim/references/ui-brand.md
 </execution_context>
 
 <context>
@@ -45,6 +45,6 @@ Context files are resolved inside the workflow via `maxsim-tools init plan-phase
 </context>
 
 <process>
-Execute the plan workflow from @./workflows/plan.md end-to-end.
+Execute the plan workflow from @~/.claude/maxsim/workflows/plan.md end-to-end.
 Preserve all workflow gates (stage detection, discussion, research, planning, gate confirmations, re-entry flow).
 </process>

package/dist/assets/templates/commands/maxsim/progress.md

@@ -16,10 +16,10 @@ Provides situational awareness before continuing work, detects phase gaps, and i
 </objective>
 
 <execution_context>
-@./workflows/progress.md
+@~/.claude/maxsim/workflows/progress.md
 </execution_context>
 
 <process>
-Execute the progress workflow from @./workflows/progress.md end-to-end.
+Execute the progress workflow from @~/.claude/maxsim/workflows/progress.md end-to-end.
 Preserve all routing logic (Routes A through F) and edge case handling.
 </process>

package/dist/assets/templates/commands/maxsim/quick.md

@@ -28,7 +28,7 @@ Quick mode is the same system with a shorter path:
 </objective>
 
 <execution_context>
-@./workflows/quick.md
+@~/.claude/maxsim/workflows/quick.md
 </execution_context>
 
 <context>
@@ -38,6 +38,6 @@ Context files are resolved inside the workflow (`init quick`) and delegated via
 </context>
 
 <process>
-Execute the quick workflow from @./workflows/quick.md end-to-end.
+Execute the quick workflow from @~/.claude/maxsim/workflows/quick.md end-to-end.
 Preserve all workflow gates (validation, task description, planning, execution, state updates, commits).
 </process>

package/dist/assets/templates/commands/maxsim/settings.md

@@ -21,11 +21,11 @@ Routes to the settings workflow which handles:
 </objective>
 
 <execution_context>
-@./workflows/settings.md
+@~/.claude/maxsim/workflows/settings.md
 </execution_context>
 
 <process>
-**Follow the settings workflow** from `@./workflows/settings.md`.
+**Follow the settings workflow** from `@~/.claude/maxsim/workflows/settings.md`.
 
 The workflow handles all logic including:
 1. Config file creation with defaults if missing

package/dist/assets/templates/references/model-profile-resolution.md

@@ -12,7 +12,7 @@ Default: `balanced` if not set or config missing.
 
 ## Lookup Table
 
-@./references/model-profiles.md
+@~/.claude/maxsim/references/model-profiles.md
 
 Look up the agent in the table for the resolved profile. Pass the model parameter to Task calls:
 

package/dist/assets/templates/references/thinking-partner.md

@@ -44,7 +44,7 @@ You are a thinking partner, not a task executor. Your role is to help the user a
 
 **Phase discussion** (discuss-phase): Focus on implementation decisions, gray area resolution, downstream impact. Challenge hand-wavy integration plans. Push for concrete acceptance criteria per deliverable.
 
-**Todo/bug triage** (add-todo --discuss, check-todos brainstorm): Focus on problem definition, scope containment, approach selection. Shorter rounds — 2-3 questions vs 4. Time-boxed to 20-30 min. Don't over-explore — capture enough to unblock, not to solve.
+**Todo/bug triage** (/maxsim:quick --todo triage): Focus on problem definition, scope containment, approach selection. Shorter rounds — 2-3 questions vs 4. Time-boxed to 20-30 min. Don't over-explore — capture enough to unblock, not to solve.
 
 **General discussion**: Default behaviors from core_behaviors apply. Read the energy — if the user is exploring, explore with them. If they want a quick answer, give it.
 

package/dist/assets/templates/references/verification-patterns.md

@@ -600,7 +600,7 @@ Some things can't be verified programmatically. Flag these for human testing:
 
 For automation-first checkpoint patterns, server lifecycle management, CLI installation handling, and error recovery protocols, see:
 
-**@./references/checkpoints.md** → `<automation_reference>` section
+**@~/.claude/maxsim/references/checkpoints.md** → `<automation_reference>` section
 
 Key principles:
 - Claude sets up verification environment BEFORE presenting checkpoints

package/dist/assets/templates/skills/github-tools-guide/SKILL.md

@@ -64,7 +64,7 @@ Add `--raw` to get machine-readable JSON output (no formatting).
 | Command | Description |
 |---------|-------------|
 | `github add-todo --title "T" [--description "D"] [--area A] [--phase P]` | Create todo issue |
-| `github complete-todo --todo-id "file.md" [--github-issue-number N]` | Complete todo |
+| `github complete-todo --todo-id "N" [--github-issue-number N]` | Complete todo |
 | `github list-todos [--area A] [--status pending\|completed\|all]` | List todos |
 
 ### Convenience

package/dist/assets/templates/templates/codebase/structure.md

@@ -216,7 +216,7 @@ maxsim/
 
 **New Workflow:**
 - Implementation: `maxsim/workflows/{name}.md`
-- Usage: Reference from command with `@./workflows/{name}.md`
+- Usage: Reference from command with `@~/.claude/maxsim/workflows/{name}.md`
 
 **New Reference Document:**
 - Implementation: `maxsim/references/{name}.md`

package/dist/assets/templates/templates/phase-prompt.md

@@ -38,10 +38,10 @@ Output: [What artifacts will be created]
 </objective>
 
 <execution_context>
-@./workflows/execute-plan.md
-@./templates/summary.md
+@~/.claude/maxsim/workflows/execute-plan.md
+@~/.claude/maxsim/templates/summary.md
 [If plan contains checkpoint tasks (type="checkpoint:*"), add:]
-@./references/checkpoints.md
+@~/.claude/maxsim/references/checkpoints.md
 </execution_context>
 
 <context>
@@ -76,7 +76,7 @@ Output: [What artifacts will be created]
   <done>[Acceptance criteria]</done>
 </task>
 
-<!-- For checkpoint task examples and patterns, see @./references/checkpoints.md -->
+<!-- For checkpoint task examples and patterns, see @~/.claude/maxsim/references/checkpoints.md -->
 <!-- Key rule: Claude starts dev server BEFORE human-verify checkpoints. User only visits URLs. -->
 
 <task type="checkpoint:decision" gate="blocking">
@@ -374,9 +374,9 @@ Output: Working dashboard component.
 </objective>
 
 <execution_context>
-@./workflows/execute-plan.md
-@./templates/summary.md
-@./references/checkpoints.md
+@~/.claude/maxsim/workflows/execute-plan.md
+@~/.claude/maxsim/templates/summary.md
+@~/.claude/maxsim/references/checkpoints.md
 </execution_context>
 
 <context>

package/dist/assets/templates/templates/state.md

@@ -56,7 +56,7 @@ Recent decisions affecting current work:
 
 ### Pending Todos
 
-[From .planning/todos/pending/ — ideas captured during sessions]
+[From GitHub Issues with label 'todo' — ideas captured during sessions]
 
 None yet.
 
@@ -145,9 +145,8 @@ Updated after each plan completion.
 
 **Decisions:** Reference to PROJECT.md Key Decisions table, plus recent decisions summary for quick access. Full decision log lives in PROJECT.md.
 
-**Pending Todos:** Ideas captured via /maxsim:quick --todo
+**Pending Todos:** Ideas captured via /maxsim:quick --todo (tracked as GitHub Issues)
 - Count of pending todos
-- Reference to .planning/todos/pending/
 - Brief list if few, count if many (e.g., "5 pending todos — see /maxsim:quick --todo")
 
 **Blockers/Concerns:** From "Next Phase Readiness" sections

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

@@ -11,7 +11,7 @@ You are a thinking partner, not an interviewer. The user is the visionary — yo
 </purpose>
 
 <required_reading>
-@./references/thinking-partner.md
+@~/.claude/maxsim/references/thinking-partner.md
 </required_reading>
 
 <tool_mandate>
@@ -612,9 +612,9 @@ Task(
     </objective>
 
     <execution_context>
-    @./workflows/plan.md
-    @./references/ui-brand.md
-    @./references/model-profile-resolution.md
+    @~/.claude/maxsim/workflows/plan.md
+    @~/.claude/maxsim/references/ui-brand.md
+    @~/.claude/maxsim/references/model-profile-resolution.md
     </execution_context>
 
     <arguments>

package/dist/assets/templates/workflows/execute-plan.md

@@ -6,7 +6,7 @@ Execute a phase plan (loaded from GitHub issue comment or local PLAN.md) and pos
 Read STATE.md before any operation to load project context.
 Read config.json for planning behavior settings.
 
-@./references/git-integration.md
+@~/.claude/maxsim/references/git-integration.md
 </required_reading>
 
 MAXSIM provides CLI commands (`github create-phase`, `github list-phases`, etc.) for structured operations.

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

@@ -8,7 +8,7 @@ Before executing any step in this workflow, verify:
 Thin orchestrator for the /maxsim:execute state machine. Detects the current state of a phase (already done, needs verification, needs execution), delegates per-plan execution to execute-plan.md subagents, runs auto-verification, and handles retry with gap closure.
 
 This file is the ORCHESTRATOR ONLY. Per-plan execution logic lives in:
-- @./workflows/execute-plan.md (per-plan subagent execution)
+- @~/.claude/maxsim/workflows/execute-plan.md (per-plan subagent execution)
 
 Verification is handled inline (spawning verifier agent) since it is a stage of this workflow, not a separate command.
 </purpose>
@@ -213,10 +213,10 @@ Execute each wave in sequence. Within a wave: parallel if `parallelization` is t
        </objective>
 
        <execution_context>
-       @./workflows/execute-plan.md
-       @./templates/summary.md
-       @./references/checkpoints.md
-       @./references/tdd.md
+       @~/.claude/maxsim/workflows/execute-plan.md
+       @~/.claude/maxsim/templates/summary.md
+       @~/.claude/maxsim/references/checkpoints.md
+       @~/.claude/maxsim/references/tdd.md
        </execution_context>
 
        <github_context>

package/dist/assets/templates/workflows/init-existing.md

@@ -6,8 +6,8 @@ Output: `.planning/` directory with config.json, PROJECT.md, REQUIREMENTS.md, RO
 
 <required_reading>
 Read all files referenced by the invoking prompt's execution_context before starting.
-@./references/thinking-partner.md
-@./references/questioning.md
+@~/.claude/maxsim/references/thinking-partner.md
+@~/.claude/maxsim/references/questioning.md
 </required_reading>
 
 <auto_mode>

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

@@ -1,10 +1,10 @@
 <purpose>
 
 Unified initialization router. Detects the current project state and delegates to the appropriate sub-workflow:
-- **New project** (no .planning/) -> delegates to @./workflows/new-project.md
-- **Existing project** (.planning/ exists, no ROADMAP.md) -> delegates to @./workflows/init-existing.md
+- **New project** (no .planning/) -> delegates to @~/.claude/maxsim/workflows/new-project.md
+- **Existing project** (.planning/ exists, no ROADMAP.md) -> delegates to @~/.claude/maxsim/workflows/init-existing.md
 - **Active milestone** (.planning/ + ROADMAP.md, phases in progress) -> shows status, offers options
-- **Milestone complete** (all phases done) -> offers completion or new milestone via @./workflows/new-milestone.md
+- **Milestone complete** (all phases done) -> offers completion or new milestone via @~/.claude/maxsim/workflows/new-milestone.md
 
 This file is a THIN ROUTER. All heavy logic lives in the sub-workflows.
 
@@ -81,7 +81,7 @@ echo "$INIT_CONTEXT"
 
 Save this JSON output — the sub-workflow will use it as `INIT_CONTEXT` and skip its own init call.
 
-Now delegate to @./workflows/new-project.md — execute the full new-project workflow end-to-end. The `INIT_CONTEXT` JSON is already loaded; the sub-workflow will detect this and skip Step 1's CLI call.
+Now delegate to @~/.claude/maxsim/workflows/new-project.md — execute the full new-project workflow end-to-end. The `INIT_CONTEXT` JSON is already loaded; the sub-workflow will detect this and skip Step 1's CLI call.
 
 Pass through:
 - `--auto` flag if set
@@ -114,7 +114,7 @@ echo "$INIT_CONTEXT"
 
 Save this JSON output — the sub-workflow will use it as `INIT_CONTEXT` and skip its own init call.
 
-Now delegate to @./workflows/init-existing.md — execute the full init-existing workflow end-to-end. The `INIT_CONTEXT` JSON is already loaded; the sub-workflow will detect this and skip Step 1's CLI call.
+Now delegate to @~/.claude/maxsim/workflows/init-existing.md — execute the full init-existing workflow end-to-end. The `INIT_CONTEXT` JSON is already loaded; the sub-workflow will detect this and skip Step 1's CLI call.
 
 Pass through:
 - `--auto` flag if set
@@ -159,7 +159,7 @@ Then present options conversationally (natural language, not AskUserQuestion):
    - If verification is pending: "Verify the current phase"
 
 2. **Start a new milestone** -- If the user wants to pivot or start fresh:
-   - Delegate to @./workflows/new-milestone.md for the milestone creation flow
+   - Delegate to @~/.claude/maxsim/workflows/new-milestone.md for the milestone creation flow
 
 3. **View detailed progress** -- Direct to `/maxsim:progress` for full status
 
@@ -189,12 +189,12 @@ Then present options conversationally:
 **Options:**
 
 1. **Complete and archive this milestone** -- Run the milestone completion flow:
-   - Delegate to @./workflows/new-milestone.md with completion mode
+   - Delegate to @~/.claude/maxsim/workflows/new-milestone.md with completion mode
    - Archives current milestone data
    - Updates MILESTONES.md with summary
 
 2. **Start a new milestone** -- Begin the next cycle:
-   - Delegate to @./workflows/new-milestone.md for creation flow
+   - Delegate to @~/.claude/maxsim/workflows/new-milestone.md for creation flow
    - Gathers new milestone goals
    - Creates fresh REQUIREMENTS.md and ROADMAP.md
 

package/dist/assets/templates/workflows/new-project.md

@@ -4,8 +4,8 @@ Initialize a new project through unified flow: questioning, research (optional),
 
 <required_reading>
 Read all files referenced by the invoking prompt's execution_context before starting.
-@./references/thinking-partner.md
-@./references/questioning.md
+@~/.claude/maxsim/references/thinking-partner.md
+@~/.claude/maxsim/references/questioning.md
 </required_reading>
 
 <auto_mode>

package/dist/assets/templates/workflows/plan-discuss.md

@@ -7,7 +7,7 @@ You are a thinking partner, not an interviewer. The user is the visionary -- you
 </purpose>
 
 <required_reading>
-@./references/thinking-partner.md
+@~/.claude/maxsim/references/thinking-partner.md
 </required_reading>
 
 <downstream_awareness>

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

@@ -8,9 +8,9 @@ Before executing any step in this workflow, verify:
 Thin orchestrator for the /maxsim:plan state machine. Detects the current stage of a phase (Discussion, Research, Planning), delegates to stage sub-workflows, shows gate confirmations between stages, and handles re-entry on already-planned phases.
 
 This file is the ORCHESTRATOR ONLY. Stage-specific logic lives in:
-- @./workflows/plan-discuss.md (Discussion stage)
-- @./workflows/plan-research.md (Research stage)
-- @./workflows/plan-create.md (Planning stage)
+- @~/.claude/maxsim/workflows/plan-discuss.md (Discussion stage)
+- @~/.claude/maxsim/workflows/plan-research.md (Research stage)
+- @~/.claude/maxsim/workflows/plan-create.md (Planning stage)
 </purpose>
 
 <process>
@@ -97,7 +97,7 @@ Wait for user choice via natural conversation.
 
 Delegate to the discussion sub-workflow for full discussion logic:
 
-@./workflows/plan-discuss.md
+@~/.claude/maxsim/workflows/plan-discuss.md
 
 Pass context: `phase_number`, `phase_name`, `phase_dir`, `padded_phase`, `phase_slug`, `commit_docs`, `roadmap_path`, `state_path`, `phase_issue_number`.
 
@@ -132,7 +132,7 @@ Wait for user response via natural conversation (not AskUserQuestion).
 
 Delegate to the research sub-workflow:
 
-@./workflows/plan-research.md
+@~/.claude/maxsim/workflows/plan-research.md
 
 Pass context: `phase_number`, `phase_name`, `phase_dir`, `padded_phase`, `phase_slug`, `commit_docs`, `researcher_model`, `research_enabled`, `has_research`, `state_path`, `roadmap_path`, `requirements_path`, `context_path`, `phase_req_ids`, `phase_issue_number`. Also pass the `--force-research` flag if present in $ARGUMENTS.
 
@@ -164,7 +164,7 @@ Wait for user response via natural conversation.
 
 Delegate to the planning sub-workflow:
 
-@./workflows/plan-create.md
+@~/.claude/maxsim/workflows/plan-create.md
 
 Pass context: `phase_number`, `phase_name`, `phase_dir`, `padded_phase`, `phase_slug`, `commit_docs`, `planner_model`, `checker_model`, `plan_checker_enabled`, `state_path`, `roadmap_path`, `requirements_path`, `context_path`, `research_path`, `phase_req_ids`, `phase_issue_number`. Also pass the `--skip-verify` flag if present in $ARGUMENTS.
 

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

@@ -588,10 +588,9 @@ Ready for next task: /maxsim:quick
 
 ```bash
 INIT=$(node ~/.claude/maxsim/bin/maxsim-tools.cjs init todos)
-mkdir -p .planning/todos/pending .planning/todos/done
 ```
 
-Extract from init JSON: `todo_count`, `todos`, `pending_dir`, `date`, `timestamp`, `github_ready`.
+Extract from init JSON: `todo_count`, `todos`, `date`, `timestamp`, `github_ready`.
 
 ---
 
@@ -646,38 +645,14 @@ If user provided a description:
 
 1. Parse priority from description (look for HIGH/MEDIUM/LOW keywords, default MEDIUM)
 2. Infer area from file paths mentioned or conversation context (default "general")
-3. Generate slug: `slug=$(node ~/.claude/maxsim/bin/maxsim-tools.cjs generate-slug "$TITLE" --raw)`
-4. Create todo file at `.planning/todos/pending/${date}-${slug}.md`:
-
-```markdown
----
-created: [timestamp]
-title: [title]
-area: [area]
-priority: [HIGH/MEDIUM/LOW]
-mode: quick
-files: []
----
-
-## Problem
-
-[description - enough context for future Claude to understand]
-
-## Solution
-
-TBD
-```
-
-5. GitHub Issue creation (primary):
+3. Create GitHub Issue (primary action):
    - Run `github add-todo` with title, priority, area, and description to create a tracked GitHub Issue (label: "todo")
-   - If GitHub is unavailable, fall back to local file only and warn user: "Todo saved locally. Run `/maxsim:init` to enable GitHub tracking."
+   - If GitHub is unavailable, warn user: "GitHub unavailable. Run `/maxsim:init` to enable GitHub tracking."
 
    ```bash
    node ~/.claude/maxsim/bin/maxsim-tools.cjs github add-todo --title "${TITLE}" --description "${DESCRIPTION}" --area "${AREA}"
    ```
-6. Local file cache: also create the local todo file for offline access
-7. Commit: `node ~/.claude/maxsim/bin/maxsim-tools.cjs commit "docs: capture todo - ${TITLE}" --files .planning/todos/pending/${date}-${slug}.md`
-8. Confirm: "Saved: ${TITLE} (priority: ${PRIORITY}) — GitHub Issue #{number}"
+4. Confirm: "Saved: ${TITLE} (priority: ${PRIORITY}) — GitHub Issue #{number}"
 
 Exit after confirm.
 
@@ -688,14 +663,12 @@ Exit after confirm.
 If user references an existing todo to complete:
 
 1. Parse identifier (number from list, or title fragment)
-2. Close the corresponding GitHub Issue (primary): run `github close-issue` with the todo's issue number
+2. Close the corresponding GitHub Issue: run `github close-issue` with the todo's issue number
 
    ```bash
    node ~/.claude/maxsim/bin/maxsim-tools.cjs github close-issue N
    ```
-3. Move local cache file: `mv ".planning/todos/pending/[filename]" ".planning/todos/done/"`
-4. Commit: `node ~/.claude/maxsim/bin/maxsim-tools.cjs commit "docs: complete todo - ${TITLE}" --files .planning/todos/done/${filename}`
-5. Confirm: "Completed: ${TITLE} — GitHub Issue closed"
+3. Confirm: "Completed: ${TITLE} — GitHub Issue closed"
 
 Exit after confirm.
 
@@ -753,8 +726,7 @@ Exit after display.
 **Todo Mode:**
 - [ ] `--todo` flag or trigger words detected
 - [ ] Todo action determined (list/capture/complete/triage)
-- [ ] (capture) Todo file created with valid frontmatter
-- [ ] (capture) Best-effort GitHub Issue creation attempted
-- [ ] (complete) Todo moved from pending to done
+- [ ] (capture) GitHub Issue created with todo label
+- [ ] (complete) GitHub Issue closed
 - [ ] (triage) Prioritized view with phase context shown
 </success_criteria>

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

@@ -8,14 +8,14 @@ Standalone research command. For most workflows, use `/maxsim:plan` which integr
 
 ## Step 0: Resolve Model Profile
 
-@./references/model-profile-resolution.md
+@~/.claude/maxsim/references/model-profile-resolution.md
 
 Resolve model for:
 - `researcher`
 
 ## Step 1: Normalize and Validate Phase
 
-@./references/phase-argument-parsing.md
+@~/.claude/maxsim/references/phase-argument-parsing.md
 
 ```bash
 PHASE_INFO=$(node ~/.claude/maxsim/bin/maxsim-tools.cjs roadmap get-phase "${PHASE}")

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

@@ -24,8 +24,8 @@ Then verify each level against the actual codebase.
 </core_principle>
 
 <required_reading>
-@./references/verification-patterns.md
-@./templates/verification-report.md
+@~/.claude/maxsim/references/verification-patterns.md
+@~/.claude/maxsim/templates/verification-report.md
 </required_reading>
 
 <process>

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

@@ -18,7 +18,7 @@ No Pass/Fail buttons. No severity questions. Just: "Here's what should happen. D
 </required_reading>
 
 <template>
-@./templates/UAT.md
+@~/.claude/maxsim/templates/UAT.md
 </template>
 
 <process>
@@ -337,7 +337,7 @@ Spawning parallel debug agents to investigate each issue.
 ```
 
 - Load diagnose-issues workflow
-- Follow @./workflows/diagnose-issues.md
+- Follow @~/.claude/maxsim/workflows/diagnose-issues.md
 - Spawn parallel debug agents for each issue
 - Collect root causes
 - Update UAT.md with root causes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "maxsimcli",
-  "version": "5.0.2",
+  "version": "5.0.3",
   "private": false,
   "description": "A meta-prompting, context engineering and spec-driven development system for Claude Code, OpenCode, Gemini and Codex by MayStudios.",
   "bin": {