get-shit-done-cc 1.7.1 → 1.9.0

package/commands/gsd/new-project.md

@@ -19,6 +19,7 @@ This is the most leveraged moment in any project. Deep questioning here means be
 - `.planning/PROJECT.md` — project context
 - `.planning/config.json` — workflow preferences
 - `.planning/research/` — domain research (optional)
+- `.planning/intel/` — codebase intelligence (auto-populated by hooks)
 - `.planning/REQUIREMENTS.md` — scoped requirements
 - `.planning/ROADMAP.md` — phase structure
 - `.planning/STATE.md` — project memory
@@ -57,7 +58,14 @@ This is the most leveraged moment in any project. Deep questioning here means be
    fi
    ```
 
-3. **Detect existing code (brownfield detection):**
+3. **Create intel directory for codebase intelligence:**
+   ```bash
+   mkdir -p .planning/intel
+   ```
+
+   This prepares the directory for the PostToolUse hook to populate with index.json, conventions.json, and summary.md as Claude writes code.
+
+4. **Detect existing code (brownfield detection):**
    ```bash
    CODE_FILES=$(find . -name "*.ts" -o -name "*.js" -o -name "*.py" -o -name "*.go" -o -name "*.rs" -o -name "*.swift" -o -name "*.java" 2>/dev/null | grep -v node_modules | grep -v .git | head -20)
    HAS_PACKAGE=$([ -f package.json ] || [ -f requirements.txt ] || [ -f Cargo.toml ] || [ -f go.mod ] || [ -f Package.swift ] && echo "yes")
@@ -237,7 +245,7 @@ EOF
 
 ## Phase 5: Workflow Preferences
 
-Ask all workflow preferences in a single AskUserQuestion call (3 questions):
+**Round 1 — Core workflow settings (4 questions):**
 
 ```
 questions: [
@@ -268,11 +276,85 @@ questions: [
       { label: "Parallel (Recommended)", description: "Independent plans run simultaneously" },
       { label: "Sequential", description: "One plan at a time" }
     ]
+  },
+  {
+    header: "Git Tracking",
+    question: "Commit planning docs to git?",
+    multiSelect: false,
+    options: [
+      { label: "Yes (Recommended)", description: "Planning docs tracked in version control" },
+      { label: "No", description: "Keep .planning/ local-only (add to .gitignore)" }
+    ]
+  }
+]
+```
+
+**Round 2 — Workflow agents:**
+
+These spawn additional agents during planning/execution. They add tokens and time but improve quality.
+
+| Agent | When it runs | What it does |
+|-------|--------------|--------------|
+| **Researcher** | Before planning each phase | Investigates domain, finds patterns, surfaces gotchas |
+| **Plan Checker** | After plan is created | Verifies plan actually achieves the phase goal |
+| **Verifier** | After phase execution | Confirms must-haves were delivered |
+
+All recommended for important projects. Skip for quick experiments.
+
+```
+questions: [
+  {
+    header: "Research",
+    question: "Spawn Plan Researcher? (researches domain before planning — adds tokens/time)",
+    multiSelect: false,
+    options: [
+      { label: "Yes (Recommended)", description: "Research phase goals before planning" },
+      { label: "No", description: "Skip research, plan directly" }
+    ]
+  },
+  {
+    header: "Plan Check",
+    question: "Spawn Plan Checker? (verifies plans before execution — adds tokens/time)",
+    multiSelect: false,
+    options: [
+      { label: "Yes (Recommended)", description: "Verify plans meet phase goals" },
+      { label: "No", description: "Skip plan verification" }
+    ]
+  },
+  {
+    header: "Verifier",
+    question: "Spawn Execution Verifier? (verifies phase completion — adds tokens/time)",
+    multiSelect: false,
+    options: [
+      { label: "Yes (Recommended)", description: "Verify must-haves after execution" },
+      { label: "No", description: "Skip post-execution verification" }
+    ]
   }
 ]
 ```
 
-Create `.planning/config.json` with chosen mode, depth, and parallelization.
+Create `.planning/config.json` with all settings:
+
+```json
+{
+  "mode": "yolo|interactive",
+  "depth": "quick|standard|comprehensive",
+  "parallelization": true|false,
+  "commit_docs": true|false,
+  "workflow": {
+    "research": true|false,
+    "plan_check": true|false,
+    "verifier": true|false
+  }
+}
+```
+
+**If commit_docs = No:**
+- Set `commit_docs: false` in config.json
+- Add `.planning/` to `.gitignore` (create if needed)
+
+**If commit_docs = Yes:**
+- Add `.planning/intel/` to `.gitignore` (intel is always local — changes constantly, can be regenerated)
 
 **Commit config.json:**
 
@@ -284,10 +366,33 @@ chore: add project config
 Mode: [chosen mode]
 Depth: [chosen depth]
 Parallelization: [enabled/disabled]
+Workflow agents: research=[on/off], plan_check=[on/off], verifier=[on/off]
 EOF
 )"
 ```
 
+**Note:** Run `/gsd:settings` anytime to update these preferences.
+
+## Phase 5.5: Resolve Model Profile
+
+Read model profile for agent spawning:
+
+```bash
+MODEL_PROFILE=$(cat .planning/config.json 2>/dev/null | grep -o '"model_profile"[[:space:]]*:[[:space:]]*"[^"]*"' | grep -o '"[^"]*"$' | tr -d '"' || echo "balanced")
+```
+
+Default to "balanced" if not set.
+
+**Model lookup table:**
+
+| Agent | quality | balanced | budget |
+|-------|---------|----------|--------|
+| gsd-project-researcher | opus | sonnet | haiku |
+| gsd-research-synthesizer | sonnet | sonnet | haiku |
+| gsd-roadmapper | opus | sonnet | sonnet |
+
+Store resolved models for use in Task calls below.
+
 ## Phase 6: Research Decision
 
 Use AskUserQuestion:
@@ -368,7 +473,7 @@ Your STACK.md feeds into roadmap creation. Be prescriptive:
 Write to: .planning/research/STACK.md
 Use template: ~/.claude/get-shit-done/templates/research-project/STACK.md
 </output>
-", subagent_type="gsd-project-researcher", description="Stack research")
+", subagent_type="gsd-project-researcher", model="{researcher_model}", description="Stack research")
 
 Task(prompt="
 <research_type>
@@ -407,7 +512,7 @@ Your FEATURES.md feeds into requirements definition. Categorize clearly:
 Write to: .planning/research/FEATURES.md
 Use template: ~/.claude/get-shit-done/templates/research-project/FEATURES.md
 </output>
-", subagent_type="gsd-project-researcher", description="Features research")
+", subagent_type="gsd-project-researcher", model="{researcher_model}", description="Features research")
 
 Task(prompt="
 <research_type>
@@ -446,7 +551,7 @@ Your ARCHITECTURE.md informs phase structure in roadmap. Include:
 Write to: .planning/research/ARCHITECTURE.md
 Use template: ~/.claude/get-shit-done/templates/research-project/ARCHITECTURE.md
 </output>
-", subagent_type="gsd-project-researcher", description="Architecture research")
+", subagent_type="gsd-project-researcher", model="{researcher_model}", description="Architecture research")
 
 Task(prompt="
 <research_type>
@@ -485,7 +590,7 @@ Your PITFALLS.md prevents mistakes in roadmap/planning. For each pitfall:
 Write to: .planning/research/PITFALLS.md
 Use template: ~/.claude/get-shit-done/templates/research-project/PITFALLS.md
 </output>
-", subagent_type="gsd-project-researcher", description="Pitfalls research")
+", subagent_type="gsd-project-researcher", model="{researcher_model}", description="Pitfalls research")
 ```
 
 After all 4 agents complete, spawn synthesizer to create SUMMARY.md:
@@ -509,7 +614,7 @@ Write to: .planning/research/SUMMARY.md
 Use template: ~/.claude/get-shit-done/templates/research-project/SUMMARY.md
 Commit after writing.
 </output>
-", subagent_type="gsd-research-synthesizer", description="Synthesize research")
+", subagent_type="gsd-research-synthesizer", model="{synthesizer_model}", description="Synthesize research")
 ```
 
 Display research complete banner and key findings:
@@ -714,7 +819,7 @@ Create roadmap:
 
 Write files first, then return. This ensures artifacts persist even if context is lost.
 </instructions>
-", subagent_type="gsd-roadmapper", description="Create roadmap")
+", subagent_type="gsd-roadmapper", model="{roadmapper_model}", description="Create roadmap")
 ```
 
 **Handle roadmapper return:**
@@ -790,7 +895,7 @@ Use AskUserQuestion:
   Update the roadmap based on feedback. Edit files in place.
   Return ROADMAP REVISED with changes made.
   </revision>
-  ", subagent_type="gsd-roadmapper", description="Revise roadmap")
+  ", subagent_type="gsd-roadmapper", model="{roadmapper_model}", description="Revise roadmap")
   ```
 - Present revised roadmap
 - Loop until user approves
@@ -865,6 +970,7 @@ Present completion with next steps:
   - `ARCHITECTURE.md`
   - `PITFALLS.md`
   - `SUMMARY.md`
+- `.planning/intel/` (created empty, populated by hooks during coding)
 - `.planning/REQUIREMENTS.md`
 - `.planning/ROADMAP.md`
 - `.planning/STATE.md`

package/commands/gsd/pause-work.md

@@ -90,6 +90,17 @@ Be specific enough for a fresh Claude to understand immediately.
 </step>
 
 <step name="commit">
+**Check planning config:**
+
+```bash
+COMMIT_PLANNING_DOCS=$(cat .planning/config.json 2>/dev/null | grep -o '"commit_docs"[[:space:]]*:[[:space:]]*[^,}]*' | grep -o 'true\|false' || echo "true")
+git check-ignore -q .planning 2>/dev/null && COMMIT_PLANNING_DOCS=false
+```
+
+**If `COMMIT_PLANNING_DOCS=false`:** Skip git operations
+
+**If `COMMIT_PLANNING_DOCS=true` (default):**
+
 ```bash
 git add .planning/phases/*/.continue-here.md
 git commit -m "wip: [phase-name] paused at task [X]/[Y]"

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

@@ -158,6 +158,17 @@ mkdir -p ".planning/phases/{NN}-{name}"
 
 ## 8. Commit Roadmap Update
 
+**Check planning config:**
+
+```bash
+COMMIT_PLANNING_DOCS=$(cat .planning/config.json 2>/dev/null | grep -o '"commit_docs"[[:space:]]*:[[:space:]]*[^,}]*' | grep -o 'true\|false' || echo "true")
+git check-ignore -q .planning 2>/dev/null && COMMIT_PLANNING_DOCS=false
+```
+
+**If `COMMIT_PLANNING_DOCS=false`:** Skip git operations
+
+**If `COMMIT_PLANNING_DOCS=true` (default):**
+
 ```bash
 git add .planning/ROADMAP.md
 git commit -m "docs(roadmap): add gap closure phases {N}-{M}"

package/commands/gsd/plan-phase.md

@@ -42,7 +42,7 @@ Normalize phase input in step 2 before any directory lookups.
 
 <process>
 
-## 1. Validate Environment
+## 1. Validate Environment and Resolve Model Profile
 
 ```bash
 ls .planning/ 2>/dev/null
@@ -50,6 +50,24 @@ ls .planning/ 2>/dev/null
 
 **If not found:** Error - user should run `/gsd:new-project` first.
 
+**Resolve model profile for agent spawning:**
+
+```bash
+MODEL_PROFILE=$(cat .planning/config.json 2>/dev/null | grep -o '"model_profile"[[:space:]]*:[[:space:]]*"[^"]*"' | grep -o '"[^"]*"$' | tr -d '"' || echo "balanced")
+```
+
+Default to "balanced" if not set.
+
+**Model lookup table:**
+
+| Agent | quality | balanced | budget |
+|-------|---------|----------|--------|
+| gsd-phase-researcher | opus | sonnet | haiku |
+| gsd-planner | opus | opus | sonnet |
+| gsd-plan-checker | sonnet | sonnet | haiku |
+
+Store resolved models for use in Task calls below.
+
 ## 2. Parse and Normalize Arguments
 
 Extract from $ARGUMENTS:
@@ -107,6 +125,14 @@ fi
 
 **If `--skip-research` flag:** Skip to step 6.
 
+**Check config for research setting:**
+
+```bash
+WORKFLOW_RESEARCH=$(cat .planning/config.json 2>/dev/null | grep -o '"research"[[:space:]]*:[[:space:]]*[^,}]*' | grep -o 'true\|false' || echo "true")
+```
+
+**If `workflow.research` is `false` AND `--research` flag NOT set:** Skip to step 6.
+
 **Otherwise:**
 
 Check for existing research:
@@ -182,6 +208,7 @@ Write research findings to: {phase_dir}/{phase}-RESEARCH.md
 Task(
   prompt=research_prompt,
   subagent_type="gsd-phase-researcher",
+  model="{researcher_model}",
   description="Research Phase {phase}"
 )
 ```
@@ -205,21 +232,26 @@ ls "${PHASE_DIR}"/*-PLAN.md 2>/dev/null
 
 **If exists:** Offer: 1) Continue planning (add more plans), 2) View existing, 3) Replan from scratch. Wait for response.
 
-## 7. Gather Context Paths
+## 7. Read Context Files
 
-Identify context files for the planner agent:
+Read and store context file contents for the planner agent. The `@` syntax does not work across Task() boundaries - content must be inlined.
 
 ```bash
-# Required
-STATE=.planning/STATE.md
-ROADMAP=.planning/ROADMAP.md
-REQUIREMENTS=.planning/REQUIREMENTS.md
-
-# Optional (created by earlier steps or commands)
-CONTEXT="${PHASE_DIR}/${PHASE}-CONTEXT.md"
-RESEARCH="${PHASE_DIR}/${PHASE}-RESEARCH.md"
-VERIFICATION="${PHASE_DIR}/${PHASE}-VERIFICATION.md"
-UAT="${PHASE_DIR}/${PHASE}-UAT.md"
+# Read required files
+STATE_CONTENT=$(cat .planning/STATE.md)
+ROADMAP_CONTENT=$(cat .planning/ROADMAP.md)
+
+# Read optional files (empty string if missing)
+REQUIREMENTS_CONTENT=$(cat .planning/REQUIREMENTS.md 2>/dev/null)
+CONTEXT_CONTENT=$(cat "${PHASE_DIR}"/*-CONTEXT.md 2>/dev/null)
+RESEARCH_CONTENT=$(cat "${PHASE_DIR}"/*-RESEARCH.md 2>/dev/null)
+
+# Gap closure files (only if --gaps mode)
+VERIFICATION_CONTENT=$(cat "${PHASE_DIR}"/*-VERIFICATION.md 2>/dev/null)
+UAT_CONTENT=$(cat "${PHASE_DIR}"/*-UAT.md 2>/dev/null)
+
+# Codebase intelligence (if exists)
+INTEL_CONTENT=$(cat .planning/intel/summary.md 2>/dev/null)
 ```
 
 ## 8. Spawn gsd-planner Agent
@@ -233,7 +265,7 @@ Display stage banner:
 ◆ Spawning planner...
 ```
 
-Fill prompt and spawn:
+Fill prompt with inlined content and spawn:
 
 ```markdown
 <planning_context>
@@ -242,23 +274,28 @@ Fill prompt and spawn:
 **Mode:** {standard | gap_closure}
 
 **Project State:**
-@.planning/STATE.md
+{state_content}
 
 **Roadmap:**
-@.planning/ROADMAP.md
+{roadmap_content}
 
 **Requirements (if exists):**
-@.planning/REQUIREMENTS.md
+{requirements_content}
 
 **Phase Context (if exists):**
-@.planning/phases/{phase_dir}/{phase}-CONTEXT.md
+{context_content}
 
 **Research (if exists):**
-@.planning/phases/{phase_dir}/{phase}-RESEARCH.md
+{research_content}
 
 **Gap Closure (if --gaps mode):**
-@.planning/phases/{phase_dir}/{phase}-VERIFICATION.md
-@.planning/phases/{phase_dir}/{phase}-UAT.md
+{verification_content}
+{uat_content}
+
+**Codebase Intel (if exists):**
+<codebase-intel>
+{intel_content}
+</codebase-intel>
 
 </planning_context>
 
@@ -288,6 +325,7 @@ Before returning PLANNING COMPLETE:
 Task(
   prompt=filled_prompt,
   subagent_type="gsd-planner",
+  model="{planner_model}",
   description="Plan Phase {phase}"
 )
 ```
@@ -299,6 +337,8 @@ Parse planner output:
 **`## PLANNING COMPLETE`:**
 - Display: `Planner created {N} plan(s). Files on disk.`
 - If `--skip-verify`: Skip to step 13
+- Check config: `WORKFLOW_PLAN_CHECK=$(cat .planning/config.json 2>/dev/null | grep -o '"plan_check"[[:space:]]*:[[:space:]]*[^,}]*' | grep -o 'true\|false' || echo "true")`
+- If `workflow.plan_check` is `false`: Skip to step 13
 - Otherwise: Proceed to step 10
 
 **`## CHECKPOINT REACHED`:**
@@ -320,7 +360,17 @@ Display:
 ◆ Spawning plan checker...
 ```
 
-Fill checker prompt and spawn:
+Read plans and requirements for the checker:
+
+```bash
+# Read all plans in phase directory
+PLANS_CONTENT=$(cat "${PHASE_DIR}"/*-PLAN.md 2>/dev/null)
+
+# Read requirements (reuse from step 7 if available)
+REQUIREMENTS_CONTENT=$(cat .planning/REQUIREMENTS.md 2>/dev/null)
+```
+
+Fill checker prompt with inlined content and spawn:
 
 ```markdown
 <verification_context>
@@ -329,10 +379,10 @@ Fill checker prompt and spawn:
 **Phase Goal:** {goal from ROADMAP}
 
 **Plans to verify:**
-@.planning/phases/{phase_dir}/*-PLAN.md
+{plans_content}
 
 **Requirements (if exists):**
-@.planning/REQUIREMENTS.md
+{requirements_content}
 
 </verification_context>
 
@@ -347,6 +397,7 @@ Return one of:
 Task(
   prompt=checker_prompt,
   subagent_type="gsd-plan-checker",
+  model="{checker_model}",
   description="Verify Phase {phase} plans"
 )
 ```
@@ -371,6 +422,12 @@ Track: `iteration_count` (starts at 1 after initial plan + check)
 
 Display: `Sending back to planner for revision... (iteration {N}/3)`
 
+Read current plans for revision context:
+
+```bash
+PLANS_CONTENT=$(cat "${PHASE_DIR}"/*-PLAN.md 2>/dev/null)
+```
+
 Spawn gsd-planner with revision prompt:
 
 ```markdown
@@ -380,7 +437,7 @@ Spawn gsd-planner with revision prompt:
 **Mode:** revision
 
 **Existing plans:**
-@.planning/phases/{phase_dir}/*-PLAN.md
+{plans_content}
 
 **Checker issues:**
 {structured_issues_from_checker}
@@ -388,7 +445,7 @@ Spawn gsd-planner with revision prompt:
 </revision_context>
 
 <instructions>
-Read existing PLAN.md files. Make targeted updates to address checker issues.
+Make targeted updates to address checker issues.
 Do NOT replan from scratch unless issues are fundamental.
 Return what changed.
 </instructions>
@@ -398,6 +455,7 @@ Return what changed.
 Task(
   prompt=revision_prompt,
   subagent_type="gsd-planner",
+  model="{planner_model}",
   description="Revise Phase {phase} plans"
 )
 ```

package/commands/gsd/progress.md

@@ -21,6 +21,12 @@ Provides situational awareness before continuing work.
 <step name="verify">
 **Verify planning structure exists:**
 
+Use Bash (not Glob) to check—Glob respects .gitignore but .planning/ is often gitignored:
+
+```bash
+test -d .planning && echo "exists" || echo "missing"
+```
+
 If no `.planning/` directory:
 
 ```
@@ -46,6 +52,7 @@ If missing both ROADMAP.md and PROJECT.md: suggest `/gsd:new-project`.
 - Read `.planning/STATE.md` for living memory (position, decisions, issues)
 - Read `.planning/ROADMAP.md` for phase structure and objectives
 - Read `.planning/PROJECT.md` for current state (What This Is, Core Value, Requirements)
+- Read `.planning/config.json` for settings (model_profile, workflow toggles)
   </step>
 
 <step name="recent">
@@ -74,6 +81,7 @@ If missing both ROADMAP.md and PROJECT.md: suggest `/gsd:new-project`.
 # [Project Name]
 
 **Progress:** [████████░░] 8/10 plans complete
+**Profile:** [quality/balanced/budget]
 
 ## Recent Work
 - [Phase X, Plan Y]: [what was accomplished - 1 line]

package/commands/gsd/query-intel.md

@@ -0,0 +1,128 @@
+---
+name: gsd:query-intel
+description: Query codebase intelligence graph for dependencies and hotspots
+argument-hint: "<dependents|hotspots> [file-path]"
+allowed-tools:
+  - Bash
+---
+
+<objective>
+Query the codebase intelligence graph database for relationship information.
+
+**Query types:**
+- `dependents <file>` — What files depend on this file? (blast radius)
+- `hotspots` — Which files have the most dependents? (change carefully)
+
+Output: Formatted query results from graph.db
+</objective>
+
+<context>
+This command exposes the graph query capabilities built by Phase 4 (Semantic Intelligence).
+
+**Use for:**
+- Checking blast radius before refactoring a core file
+- Identifying high-impact files that need careful changes
+- Understanding dependency relationships in the codebase
+
+**Requires:** `.planning/intel/graph.db` (created by `/gsd:analyze-codebase` with entity generation)
+
+If graph.db doesn't exist, the command will return an error suggesting to run analyze-codebase first.
+</context>
+
+<process>
+
+## Step 1: Parse arguments
+
+Extract query type and optional file path from arguments.
+
+**Arguments:** $ARGUMENTS
+
+**Expected formats:**
+- `dependents src/lib/db.ts` — query what depends on this file
+- `hotspots` — query most-depended-on files
+- `hotspots 10` — query top 10 hotspots (default: 5)
+
+## Step 2: Convert file path to entity ID
+
+For `dependents` queries, convert the file path to entity ID format:
+- `src/lib/db.ts` → `src-lib-db`
+- Replace `/` with `-`, remove extension
+
+```bash
+# Example conversion
+FILE_PATH="src/lib/db.ts"
+ENTITY_ID=$(echo "$FILE_PATH" | sed 's/\.[^.]*$//' | tr '/' '-')
+```
+
+## Step 3: Execute query
+
+Run the appropriate query against the graph database:
+
+**For dependents:**
+```bash
+echo '{"action":"query","type":"dependents","target":"'$ENTITY_ID'","limit":20}' | node hooks/gsd-intel-index.js
+```
+
+**For hotspots:**
+```bash
+echo '{"action":"query","type":"hotspots","limit":5}' | node hooks/gsd-intel-index.js
+```
+
+## Step 4: Format and present results
+
+Parse the JSON response and present in readable format.
+
+**For dependents:**
+```
+## Files that depend on {file-path}
+
+Found {count} dependents:
+
+1. src/api/users.ts
+2. src/api/auth.ts
+3. src/services/payment.ts
+...
+
+**Blast radius:** {count} files would be affected by changes.
+```
+
+**For hotspots:**
+```
+## Dependency Hotspots
+
+These files have the most dependents — change carefully:
+
+| Rank | File | Dependents |
+|------|------|------------|
+| 1 | src/lib/db.ts | 42 |
+| 2 | src/types/user.ts | 35 |
+| 3 | src/utils/format.ts | 28 |
+```
+
+## Step 5: Handle errors
+
+**If graph.db doesn't exist:**
+```
+No graph database found at .planning/intel/graph.db
+
+Run /gsd:analyze-codebase first to build the dependency graph.
+```
+
+**If entity not found:**
+```
+No entity found for: {file-path}
+
+The file may not be indexed yet. Try:
+- /gsd:analyze-codebase to rebuild the index
+- Check the file path is correct
+```
+
+</process>
+
+<success_criteria>
+- [ ] Query type parsed from arguments
+- [ ] File path converted to entity ID (for dependents)
+- [ ] Query executed against graph.db
+- [ ] Results formatted in readable markdown
+- [ ] Errors handled gracefully with helpful messages
+</success_criteria>

package/commands/gsd/quick.md

@@ -34,6 +34,27 @@ Orchestration is inline - no separate workflow file. Quick mode is deliberately
 </context>
 
 <process>
+**Step 0: Resolve Model Profile**
+
+Read model profile for agent spawning:
+
+```bash
+MODEL_PROFILE=$(cat .planning/config.json 2>/dev/null | grep -o '"model_profile"[[:space:]]*:[[:space:]]*"[^"]*"' | grep -o '"[^"]*"$' | tr -d '"' || echo "balanced")
+```
+
+Default to "balanced" if not set.
+
+**Model lookup table:**
+
+| Agent | quality | balanced | budget |
+|-------|---------|----------|--------|
+| gsd-planner | opus | opus | sonnet |
+| gsd-executor | opus | sonnet | sonnet |
+
+Store resolved models for use in Task calls below.
+
+---
+
 **Step 1: Pre-flight validation**
 
 Check that an active GSD project exists:
@@ -145,6 +166,7 @@ Return: ## PLANNING COMPLETE with plan path
 </output>
 ",
   subagent_type="gsd-planner",
+  model="{planner_model}",
   description="Quick plan: ${DESCRIPTION}"
 )
 ```
@@ -178,6 +200,7 @@ Project state: @.planning/STATE.md
 </constraints>
 ",
   subagent_type="gsd-executor",
+  model="{executor_model}",
   description="Execute: ${DESCRIPTION}"
 )
 ```