@ktpartners/dgs-platform 2.8.0 → 3.0.4

package/commands/dgs/map-codebase.md

@@ -1,6 +1,6 @@
 ---
 name: dgs:map-codebase
-description: Analyze registered repos with parallel mapper agents to produce per-repo .planning/codebase/<repo>/ documents and cross-repo analysis
+description: Analyze registered repos with parallel mapper agents to produce per-repo codebase/<repo>/ documents and cross-repo analysis
 argument-hint: "[<repo-name>]"
 allowed-tools:
   - Read
@@ -18,9 +18,9 @@ Supports two modes:
 - **Refresh mode** (default, no flags): Clears all existing codebase maps and remaps everything from scratch.
 - **Update mode** (`<repo-name>` or `--only <repo-name>`): Re-maps only the specified repo and regenerates unified files from all repos.
 
-Reads REPOS.md to discover registered repos, then spawns 4 mapper agents per repo (or just the targeted repo in update mode). Each agent explores the repo's actual path and writes documents directly to `.planning/codebase/<repo-name>/`. The orchestrator only receives confirmations.
+Reads REPOS.md to discover registered repos, then spawns 4 mapper agents per repo (or just the targeted repo in update mode). Each agent explores the repo's actual path and writes documents directly to `codebase/<repo-name>/`. The orchestrator only receives confirmations.
 
-Output: .planning/codebase/<repo-name>/ folders, each with 7 structured documents about that repo's codebase state, plus 7 unified top-level files synthesized from per-repo content, plus CROSS-REPO.md with cross-repo comparison tables (when 2+ repos).
+Output: codebase/<repo-name>/ folders, each with 7 structured documents about that repo's codebase state, plus 7 unified top-level files synthesized from per-repo content, plus CROSS-REPO.md with cross-repo comparison tables (when 2+ repos).
 </objective>
 
 <execution_context>
@@ -31,7 +31,7 @@ Output: .planning/codebase/<repo-name>/ folders, each with 7 structured document
 **Reads REPOS.md** to discover registered repos and their paths.
 
 **Load project state if exists:**
-Check for .planning/STATE.md - loads context if project already initialized
+Check for ${state_path} - loads context if project already initialized
 
 **This command can run:**
 - Before /dgs:new-project (brownfield codebases) - creates codebase maps first
@@ -60,7 +60,7 @@ Check for .planning/STATE.md - loads context if project already initialized
 3. Mode-aware cleanup:
    - Refresh: Delete all existing codebase docs and per-repo subdirectories
    - Update: Delete only the targeted repo's subdirectory (other repos untouched)
-4. Create .planning/codebase/<repo-name>/ directories (all repos or just targeted repo)
+4. Create codebase/<repo-name>/ directories (all repos or just targeted repo)
 5. Spawn 4 parallel dgs-codebase-mapper agents per repo (all run in parallel):
    - Agent 1: tech focus -> writes STACK.md, INTEGRATIONS.md
    - Agent 2: arch focus -> writes ARCHITECTURE.md, STRUCTURE.md
@@ -78,7 +78,7 @@ Check for .planning/STATE.md - loads context if project already initialized
 </process>
 
 <success_criteria>
-- [ ] .planning/codebase/<repo-name>/ directories created for each registered repo (or targeted repo in update mode)
+- [ ] codebase/<repo-name>/ directories created for each registered repo (or targeted repo in update mode)
 - [ ] All 7 codebase documents written per repo by mapper agents
 - [ ] Documents follow template structure
 - [ ] Parallel agents completed without errors

package/commands/dgs/new-milestone.md

@@ -15,11 +15,11 @@ Start a new milestone: questioning → research (optional) → requirements →
 Brownfield equivalent of new-project. Project exists, PROJECT.md has history. Gathers "what's next", updates PROJECT.md, then runs requirements → roadmap cycle.
 
 **Creates/Updates:**
-- `.planning/PROJECT.md` — updated with new milestone goals
-- `.planning/research/` — domain research (optional, NEW features only)
-- `.planning/REQUIREMENTS.md` — scoped requirements for this milestone
-- `.planning/ROADMAP.md` — phase structure (continues numbering)
-- `.planning/STATE.md` — reset for new milestone
+- `${project_path}` — updated with new milestone goals
+- `${project_root}/research/` — domain research (optional, NEW features only)
+- `${project_root}/REQUIREMENTS.md` — scoped requirements for this milestone
+- `${roadmap_path}` — phase structure (continues numbering)
+- `${state_path}` — reset for new milestone
 
 **After:** `/dgs:plan-phase [N]` to start execution.
 </objective>

package/commands/dgs/new-project.md

@@ -18,12 +18,12 @@ allowed-tools:
 Initialize a new project through unified flow: questioning → research (optional) → requirements → roadmap.
 
 **Creates:**
-- `.planning/PROJECT.md` — project context
-- `.planning/config.json` — workflow preferences
-- `.planning/research/` — domain research (optional)
-- `.planning/REQUIREMENTS.md` — scoped requirements
-- `.planning/ROADMAP.md` — phase structure
-- `.planning/STATE.md` — project memory
+- `${project_path}` — project context
+- `config.json` — workflow preferences
+- `${project_root}/research/` — domain research (optional)
+- `${project_root}/REQUIREMENTS.md` — scoped requirements
+- `${roadmap_path}` — phase structure
+- `${state_path}` — project memory
 
 **After this command:** Run `/dgs:plan-phase 1` to start execution.
 </objective>

package/commands/dgs/plan-milestone-gaps.md

@@ -23,7 +23,7 @@ One command creates all fix phases — no manual `/dgs:add-phase` per gap.
 
 <context>
 **Audit results:**
-Glob: .planning/v*-MILESTONE-AUDIT.md (use most recent)
+Glob: ${project_root}/v*-MILESTONE-AUDIT.md (use most recent)
 
 Original intent and current planning state are loaded on demand inside the workflow.
 </context>

package/commands/dgs/progress.md

@@ -1,6 +1,6 @@
 ---
 name: dgs:progress
-description: Check project progress, show context, and route to next action (execute or plan)
+description: Check project progress, show context, and route to next action (execute or plan). Use --all for product-wide dashboard across all projects
 allowed-tools:
   - Read
   - Bash
@@ -16,9 +16,9 @@ Provides situational awareness before continuing work.
 
 <execution_context>
 @~/.claude/deliver-great-systems/workflows/progress.md
+@~/.claude/deliver-great-systems/workflows/progress-all.md
 </execution_context>
 
 <process>
-Execute the progress workflow from @~/.claude/deliver-great-systems/workflows/progress.md end-to-end.
-Preserve all routing logic (Routes A through F) and edge case handling.
+Parse $ARGUMENTS. If it contains the `--all` flag, execute the product-level dashboard workflow from @~/.claude/deliver-great-systems/workflows/progress-all.md end-to-end. Otherwise, execute the single-project progress workflow from @~/.claude/deliver-great-systems/workflows/progress.md end-to-end, preserving all routing logic (Routes A through F) and edge case handling.
 </process>

package/commands/dgs/quick-abandon.md

@@ -0,0 +1,8 @@
+---
+name: dgs:quick-abandon
+description: "Alias for /dgs:abandon-quick"
+allowed-tools: []
+---
+This command has been renamed. Use `/dgs:abandon-quick` instead.
+
+Run `/dgs:abandon-quick $ARGUMENTS` to continue.

package/commands/dgs/quick-complete.md

@@ -0,0 +1,8 @@
+---
+name: dgs:quick-complete
+description: "Alias for /dgs:complete-quick"
+allowed-tools: []
+---
+This command has been renamed. Use `/dgs:complete-quick` instead.
+
+Run `/dgs:complete-quick $ARGUMENTS` to continue.

package/commands/dgs/quick.md

@@ -1,7 +1,7 @@
 ---
 name: dgs:quick
 description: Execute a quick task with DGS guarantees (atomic commits, state tracking) but skip optional agents
-argument-hint: "[--full]"
+argument-hint: "[--full] [--debug] [--main]"
 allowed-tools:
   - Read
   - Write
@@ -17,12 +17,19 @@ Execute small, ad-hoc tasks with DGS guarantees (atomic commits, STATE.md tracki
 
 Quick mode is the same system with a shorter path:
 - Spawns dgs-planner (quick mode) + dgs-executor(s)
-- Quick tasks live in `.planning/quick/` separate from planned phases
+- Quick tasks live in `quick/` separate from planned phases
 - Updates STATE.md "Quick Tasks Completed" table (NOT ROADMAP.md)
 
+**Two flavors (auto-detected):**
+- **Product-level quick** (no active milestone, or `--main` flag): Creates an ephemeral worktree off main with a `quick/{slug}` branch. Use `/dgs:complete-quick` to rebase, merge, and clean up. Use `/dgs:abandon-quick` to discard.
+- **Milestone-context quick** (active milestone): Works within the existing milestone worktree. No new worktree created. Changes merge with the milestone via `/dgs:complete-milestone`.
+
 **Default:** Skips research, plan-checker, verifier. Use when you know exactly what to do.
 
-**`--full` flag:** Enables plan-checking (max 2 iterations) and post-execution verification. Use when you want quality guarantees without full milestone ceremony.
+**Flags:**
+- **`--full`:** Enables plan-checking (max 2 iterations) and post-execution verification. Use when you want quality guarantees without full milestone ceremony.
+- **`--debug`:** Investigation-focused guidance. Agent investigates root cause before fixing, documents findings. May result in no code change. Same git mechanics.
+- **`--main`:** Forces product-level quick even when a milestone is active. Creates its own worktree instead of working in the milestone worktree.
 </objective>
 
 <execution_context>

package/commands/dgs/research-idea.md

@@ -19,7 +19,7 @@ Research an idea's technical landscape and feasibility through a subagent workfl
 - **With an idea ID** (`/dgs:research-idea 5`): Researches that specific idea directly
 - **Without an idea ID** (`/dgs:research-idea`): Lists pending ideas for selection
 
-The output is a research document at `.planning/docs/ideas/pending/{slug}-research.md` and a Research Log entry appended to the idea file, both committed together. When prior research exists, the document is overwritten with a "Changes from Prior Research" section highlighting what shifted.
+The output is a research document at `${project_root}/docs/ideas/pending/{slug}-research.md` and a Research Log entry appended to the idea file, both committed together. When prior research exists, the document is overwritten with a "Changes from Prior Research" section highlighting what shifted.
 </objective>
 
 <execution_context>
@@ -37,7 +37,7 @@ The workflow handles all logic including:
 1. Argument parsing and idea selection (with or without ID)
 2. Loading idea context and prior research/discussion history
 3. Five adaptive research dimensions (web search, codebase analysis, landscape survey, approach identification, feasibility assessment)
-4. Research document creation at `.planning/docs/ideas/pending/{slug}-research.md`
+4. Research document creation at `${project_root}/docs/ideas/pending/{slug}-research.md`
 5. Research log entry save via `dgs-tools.cjs ideas research-save`
 6. Git commit of both files and next-step suggestion
 </process>

package/commands/dgs/research-phase.md

@@ -55,7 +55,7 @@ PHASE_INFO=$(node ~/.claude/deliver-great-systems/bin/dgs-tools.cjs roadmap get-
 ## 2. Check Existing Research
 
 ```bash
-ls .planning/phases/${PHASE}-*/RESEARCH.md 2>/dev/null
+ls ${project_root}/phases/${PHASE}-*/RESEARCH.md 2>/dev/null
 ```
 
 **If exists:** Offer: 1) Update research, 2) View existing, 3) Skip. Wait for response.
@@ -129,7 +129,7 @@ Before declaring complete, verify:
 </quality_gate>
 
 <output>
-Write to: .planning/phases/${PHASE}-{slug}/${PHASE}-RESEARCH.md
+Write to: ${project_root}/phases/${PHASE}-{slug}/${PHASE}-RESEARCH.md
 </output>
 ```
 
@@ -159,7 +159,7 @@ Continue research for Phase {phase_number}: {phase_name}
 
 <prior_state>
 <files_to_read>
-- .planning/phases/${PHASE}-{slug}/${PHASE}-RESEARCH.md (Existing research)
+- ${project_root}/phases/${PHASE}-{slug}/${PHASE}-RESEARCH.md (Existing research)
 </files_to_read>
 </prior_state>
 

package/commands/dgs/switch-project.md

@@ -10,7 +10,7 @@ allowed-tools:
 <objective>
 Switch the active project context. If a project name is provided, switches immediately. If no name is given, shows a picker with all active projects.
 
-After switching, all DGS commands operate in the new project's context (its .planning/ directory, repos, and state).
+After switching, all DGS commands operate in the new project's context (its project directory, repos, and state).
 </objective>
 
 <process>

package/commands/dgs/write-spec.md

@@ -28,9 +28,9 @@ The spec covers the full lifecycle: idea selection, PRD generation with all requ
 Arguments: $ARGUMENTS (optional idea IDs and `--auto` flag)
 
 Codebase context for Technical Considerations:
-@.planning/codebase/ARCHITECTURE.md
-@.planning/codebase/STACK.md
-@.planning/codebase/STRUCTURE.md
+@codebase/ARCHITECTURE.md
+@codebase/STACK.md
+@codebase/STRUCTURE.md
 </context>
 
 <process>