feat(gsd-tools): add compound init commands and update workflows (#468)

* feat(gsd-tools): add compound init commands for workflow setup

Adds 8 compound commands that return all context a workflow needs in
one JSON blob, replacing 5-10 atomic calls per workflow:

- init execute-phase: models, config, phase info, plan inventory
- init plan-phase: models, workflow flags, existing artifacts
- init new-project: models, brownfield detection, state checks
- init new-milestone: models, milestone info
- init quick: models, next task number, timestamps
- init resume: file existence, interrupted agent
- init verify-work: models, phase info
- init phase-op: generic phase context

Updated 8 workflows to use compound commands:
- execute-phase, plan-phase, new-project, quick
- resume-project, verify-work, discuss-phase

Token savings: ~200 lines of bash setup replaced with single init calls.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* feat(gsd-tools): add 4 new init commands and update files to use compound commands

Add new compound init commands:
- init todos - context for todo workflows
- init milestone-op - context for milestone operations
- init map-codebase - context for codebase mapping
- init progress - context for progress workflow

Update 24 files to use compound init commands instead of atomic calls:
- 4 phase operation workflows (add-phase, insert-phase, remove-phase, verify-phase)
- 5 todo/milestone workflows (add-todo, check-todos, audit-milestone, complete-milestone, new-milestone)
- 6 misc workflows (execute-plan, map-codebase, pause-work, progress, set-profile, settings)
- 6 agent files (gsd-executor, gsd-planner, gsd-phase-researcher, gsd-plan-checker, gsd-debugger, gsd-research-synthesizer)
- 2 command files (debug, research-phase)
- 1 reference file (planning-config)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix(gsd-tools): add init to help output

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* fix(verify-phase): correct expected init fields

The workflow was referencing plans/summaries from init phase-op,
but those fields come from ls command. Updated to reference
has_plans and plan_count which are actually in phase-op output.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>

agents/gsd-debugger.md

@@ -979,10 +979,11 @@ mkdir -p .planning/debug/resolved
 mv .planning/debug/{slug}.md .planning/debug/resolved/
 ```
 
-**Check planning config:**
+**Check planning config using state load (commit_docs is available from the output):**
 
 ```bash
-COMMIT_PLANNING_DOCS=$(node ~/.claude/get-shit-done/bin/gsd-tools.js state load --raw | grep '^commit_docs=' | cut -d= -f2)
+INIT=$(node ~/.claude/get-shit-done/bin/gsd-tools.js state load)
+# commit_docs is in the JSON output
 ```
 
 **Commit the fix:**

agents/gsd-executor.md

@@ -16,22 +16,21 @@ Your job: Execute the plan completely, commit each task, create SUMMARY.md, upda
 <execution_flow>
 
 <step name="load_project_state" priority="first">
-Read project state:
+Load execution context:
 
+```bash
+INIT=$(node ~/.claude/get-shit-done/bin/gsd-tools.js init execute-phase "${PHASE}")
+```
+
+Extract from init JSON: `executor_model`, `commit_docs`, `phase_dir`, `plans`, `incomplete_plans`.
+
+Also read STATE.md for position, decisions, blockers:
 ```bash
 cat .planning/STATE.md 2>/dev/null
 ```
 
-Parse: current position, accumulated decisions, blockers/concerns.
-
 If STATE.md missing but .planning/ exists: offer to reconstruct or continue without.
 If .planning/ missing: Error — project not initialized.
-
-**Load planning config:**
-
-```bash
-COMMIT_PLANNING_DOCS=$(node ~/.claude/get-shit-done/bin/gsd-tools.js state load --raw | grep '^commit_docs=' | cut -d= -f2)
-```
 </step>
 
 <step name="load_plan">

agents/gsd-phase-researcher.md

@@ -293,11 +293,16 @@ Verified patterns from official sources:
 
 Orchestrator provides: phase number/name, description/goal, requirements, constraints, output path.
 
+Load phase context using init command:
 ```bash
-PHASE_DIR=$(node ~/.claude/get-shit-done/bin/gsd-tools.js find-phase "$PHASE" --raw)
-PADDED_PHASE=$(node ~/.claude/get-shit-done/bin/gsd-tools.js find-phase "$PHASE" | grep -o '"phase_number":"[^"]*"' | cut -d'"' -f4)
+INIT=$(node ~/.claude/get-shit-done/bin/gsd-tools.js init phase-op "${PHASE}")
+```
 
-cat "$PHASE_DIR"/*-CONTEXT.md 2>/dev/null
+Extract from init JSON: `phase_dir`, `padded_phase`, `phase_number`, `commit_docs`.
+
+Then read CONTEXT.md if exists:
+```bash
+cat "$phase_dir"/*-CONTEXT.md 2>/dev/null
 ```
 
 **If CONTEXT.md exists**, it constrains research:

agents/gsd-plan-checker.md

@@ -297,13 +297,19 @@ issue:
 
 ## Step 1: Load Context
 
+Load phase operation context:
+```bash
+INIT=$(node ~/.claude/get-shit-done/bin/gsd-tools.js init phase-op "${PHASE_ARG}")
+```
+
+Extract from init JSON: `phase_dir`, `phase_number`, `has_plans`, `plan_count`.
+
 Orchestrator provides CONTEXT.md content in the verification prompt. If provided, parse for locked decisions, discretion areas, deferred ideas.
 
 ```bash
-PHASE_DIR=$(node ~/.claude/get-shit-done/bin/gsd-tools.js find-phase "$PHASE_ARG" --raw)
-ls "$PHASE_DIR"/*-PLAN.md 2>/dev/null
-grep -A 10 "Phase $PHASE_NUM" .planning/ROADMAP.md | head -15
-ls "$PHASE_DIR"/*-BRIEF.md 2>/dev/null
+ls "$phase_dir"/*-PLAN.md 2>/dev/null
+grep -A 10 "Phase $phase_number" .planning/ROADMAP.md | head -15
+ls "$phase_dir"/*-BRIEF.md 2>/dev/null
 ```
 
 **Extract:** Phase goal, requirements (decompose goal), locked decisions, deferred ideas.

agents/gsd-planner.md

@@ -683,14 +683,14 @@ Triggered by `--gaps` flag. Creates plans to address verification or UAT failure
 
 **1. Find gap sources:**
 
-```bash
-PHASE_DIR=$(node ~/.claude/get-shit-done/bin/gsd-tools.js find-phase "$PHASE_ARG" --raw)
+Use init context (from load_project_state) which provides `phase_dir`:
 
+```bash
 # Check for VERIFICATION.md (code verification gaps)
-ls "$PHASE_DIR"/*-VERIFICATION.md 2>/dev/null
+ls "$phase_dir"/*-VERIFICATION.md 2>/dev/null
 
 # Check for UAT.md with diagnosed status (user testing gaps)
-grep -l "status: diagnosed" "$PHASE_DIR"/*-UAT.md 2>/dev/null
+grep -l "status: diagnosed" "$phase_dir"/*-UAT.md 2>/dev/null
 ```
 
 **2. Parse gaps:** Each gap has: truth (failed behavior), reason, artifacts (files with issues), missing (things to add/fix).
@@ -830,15 +830,20 @@ node ~/.claude/get-shit-done/bin/gsd-tools.js commit "fix($PHASE): revise plans
 <execution_flow>
 
 <step name="load_project_state" priority="first">
-Read `.planning/STATE.md` — parse current position, accumulated decisions, pending todos, blockers/concerns.
-
-If STATE.md missing but .planning/ exists, offer to reconstruct or continue without.
-
-**Load planning config:**
+Load planning context:
 
 ```bash
-COMMIT_PLANNING_DOCS=$(node ~/.claude/get-shit-done/bin/gsd-tools.js state load --raw | grep '^commit_docs=' | cut -d= -f2)
+INIT=$(node ~/.claude/get-shit-done/bin/gsd-tools.js init plan-phase "${PHASE}")
 ```
+
+Extract from init JSON: `planner_model`, `researcher_model`, `checker_model`, `commit_docs`, `research_enabled`, `phase_dir`, `phase_number`, `has_research`, `has_context`.
+
+Also read STATE.md for position, decisions, blockers:
+```bash
+cat .planning/STATE.md 2>/dev/null
+```
+
+If STATE.md missing but .planning/ exists, offer to reconstruct or continue without.
 </step>
 
 <step name="load_codebase_context">
@@ -905,17 +910,17 @@ done
 </step>
 
 <step name="gather_phase_context">
-```bash
-PHASE_DIR=$(node ~/.claude/get-shit-done/bin/gsd-tools.js find-phase "$PHASE" --raw)
+Use `phase_dir` from init context (already loaded in load_project_state).
 
-cat "$PHASE_DIR"/*-CONTEXT.md 2>/dev/null   # From /gsd:discuss-phase
-cat "$PHASE_DIR"/*-RESEARCH.md 2>/dev/null   # From /gsd:research-phase
-cat "$PHASE_DIR"/*-DISCOVERY.md 2>/dev/null  # From mandatory discovery
+```bash
+cat "$phase_dir"/*-CONTEXT.md 2>/dev/null   # From /gsd:discuss-phase
+cat "$phase_dir"/*-RESEARCH.md 2>/dev/null   # From /gsd:research-phase
+cat "$phase_dir"/*-DISCOVERY.md 2>/dev/null  # From mandatory discovery
 ```
 
-**If CONTEXT.md exists:** Honor user's vision, prioritize essential features, respect boundaries. Locked decisions — do not revisit.
+**If CONTEXT.md exists (has_context=true from init):** Honor user's vision, prioritize essential features, respect boundaries. Locked decisions — do not revisit.
 
-**If RESEARCH.md exists:** Use standard_stack, architecture_patterns, dont_hand_roll, common_pitfalls.
+**If RESEARCH.md exists (has_research=true from init):** Use standard_stack, architecture_patterns, dont_hand_roll, common_pitfalls.
 </step>
 
 <step name="break_into_tasks">