@tekyzinc/gsd-t 3.12.15 → 3.13.11

package/commands/gsd-t-gap-analysis.md

@@ -4,6 +4,10 @@ You are performing a gap analysis between a provided specification and the exist
 
 ## Step 0.5: Scan Freshness Auto-Refresh
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-gap-analysis --step 0 --step-label ".5: Scan Freshness Auto-Refresh" 2>/dev/null || true
+```
+
 Before reading scan data for gap classification, check if scan docs are stale and auto-refresh if needed. This ensures gap analysis is based on current code — no warnings, no user involvement.
 
 If `.gsd-t/scan/.cache.json` exists:
@@ -21,6 +25,10 @@ If `.gsd-t/scan/` doesn't exist at all → skip (no scan data to refresh).
 
 ## Step 1: Load Context
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-gap-analysis --step 1 --step-label "Load Context" 2>/dev/null || true
+```
+
 Read (if they exist):
 1. `CLAUDE.md` — project context
 2. `.gsd-t/progress.md` — current state
@@ -29,6 +37,10 @@ Read (if they exist):
 
 ## Step 1.5: Graph-Enhanced Code Mapping
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-gap-analysis --step 1 --step-label ".5: Graph-Enhanced Code Mapping" 2>/dev/null || true
+```
+
 If `.gsd-t/graph/meta.json` exists (graph index is available):
 1. Query `getRequirementFor` to pre-map requirements to code entities — provides evidence for classification in Step 4
 2. Query `findDeadCode` to identify unreachable code that may indicate implemented-but-disconnected features (potential gap indicators)
@@ -38,6 +50,10 @@ If graph is not available, skip this step.
 
 ## Step 2: Parse Requirements
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-gap-analysis --step 2 --step-label "Parse Requirements" 2>/dev/null || true
+```
+
 Break the provided spec into numbered discrete requirements. Each requirement should be:
 - **Atomic** — one testable behavior or capability per item
 - **Clear** — unambiguous language
@@ -61,6 +77,10 @@ For large specs, show progress: "Analyzing section {N} of {total}: {section name
 
 ## Step 3: Clarification Check
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-gap-analysis --step 3 --step-label "Clarification Check" 2>/dev/null || true
+```
+
 Review each requirement for ambiguity. If any are unclear:
 
 - At **Level 3 (Full Auto)**: Proceed with reasonable assumptions. Flag each assumption in the gap analysis with `[ASSUMED: {assumption}]`
@@ -76,6 +96,10 @@ Discuss now or proceed with assumptions?
 
 ## Step 4: System Scan + Gap Classification (Team Mode)
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-gap-analysis --step 4 --step-label "System Scan + Gap Classification (Team Mode)" 2>/dev/null || true
+```
+
 Automatically use agent teams to scan and classify requirements in parallel.
 
 ### Team Distribution Strategy
@@ -152,6 +176,10 @@ If agent teams are not available or there are fewer than 3 requirements, run seq
 
 ## Step 6: Generate Gap Analysis Document
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-gap-analysis --step 6 --step-label "Generate Gap Analysis Document" 2>/dev/null || true
+```
+
 Create `.gsd-t/gap-analysis.md`:
 
 ```markdown
@@ -205,6 +233,10 @@ Create `.gsd-t/gap-analysis.md`:
 
 ## Step 7: Merge to Requirements (Optional)
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-gap-analysis --step 7 --step-label "Merge to Requirements (Optional)" 2>/dev/null || true
+```
+
 After generating the gap analysis, offer:
 
 ```
@@ -218,6 +250,10 @@ If yes, merge the discrete requirements into `docs/requirements.md`, marking eac
 
 ## Step 8: Present Promotion Options
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-gap-analysis --step 8 --step-label "Present Promotion Options" 2>/dev/null || true
+```
+
 Show the recommended groupings and offer promotion paths:
 
 ```
@@ -239,6 +275,10 @@ At **Level 3**: Present the recommendations and wait for user direction. Do NOT
 
 ## Step 9: Re-run Support
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-gap-analysis --step 9 --step-label "Re-run Support" 2>/dev/null || true
+```
+
 If `.gsd-t/gap-analysis.md` already exists from a previous run:
 
 1. Read the previous gap analysis

package/commands/gsd-t-integrate.md

@@ -25,6 +25,10 @@ Per `.gsd-t/contracts/model-selection-contract.md` v1.0.0.
 
 ## Step 1: Load Full State
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-integrate --step 1 --step-label "Load Full State" 2>/dev/null || true
+```
+
 Read everything:
 1. `CLAUDE.md`
 2. `.gsd-t/progress.md`
@@ -35,6 +39,10 @@ Read everything:
 
 ## Step 1.5: Graph-Enhanced Integration Validation
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-integrate --step 1 --step-label ".5: Graph-Enhanced Integration Validation" 2>/dev/null || true
+```
+
 If `.gsd-t/graph/meta.json` exists (graph index is available):
 1. Query `getDomainBoundaryViolations` to validate that cross-domain wiring matches contracts — flag any code that crosses boundaries without a contract
 2. Query `getCallers` and `getCallees` across domain boundaries to verify all integration points are accounted for in `integration-points.md`
@@ -44,6 +52,10 @@ If graph is not available, skip this step.
 
 ## Step 2: Contract Compliance Audit
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-integrate --step 2 --step-label "Contract Compliance Audit" 2>/dev/null || true
+```
+
 Before wiring anything together, verify each domain honored its contracts:
 
 For each contract file:
@@ -73,6 +85,10 @@ Fix any mismatches BEFORE proceeding to integration.
 
 ## Step 2.5: Worktree Merge Status Check
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-integrate --step 2 --step-label ".5: Worktree Merge Status Check" 2>/dev/null || true
+```
+
 Before wiring integration points, check whether team mode execution left any domains with rolled-back worktree merges:
 
 1. Read `.gsd-t/progress.md` — look for `[rollback]` entries in the Decision Log from the execute phase
@@ -83,6 +99,10 @@ If rolled-back domains exist, report them to the user (or if Level 3: log to `.g
 
 ## Step 3: Wire Integration Points
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-integrate --step 3 --step-label "Wire Integration Points" 2>/dev/null || true
+```
+
 **Stack Rules Detection (before spawning subagent):**
 Run via Bash to detect project stack and collect matching rules:
 `GSD_T_DIR=$(npm root -g 2>/dev/null)/@tekyzinc/gsd-t; STACKS_DIR="$GSD_T_DIR/templates/stacks"; STACK_RULES=""; if [ -d "$STACKS_DIR" ]; then for f in "$STACKS_DIR"/_*.md; do [ -f "$f" ] && STACK_RULES="${STACK_RULES}$(cat "$f")"$'\n\n'; done; if [ -f "package.json" ]; then grep -q '"react"' package.json 2>/dev/null && [ -f "$STACKS_DIR/react.md" ] && STACK_RULES="${STACK_RULES}$(cat "$STACKS_DIR/react.md")"$'\n\n'; (grep -q '"typescript"' package.json 2>/dev/null || [ -f "tsconfig.json" ]) && [ -f "$STACKS_DIR/typescript.md" ] && STACK_RULES="${STACK_RULES}$(cat "$STACKS_DIR/typescript.md")"$'\n\n'; grep -qE '"(express|fastify|hono|koa)"' package.json 2>/dev/null && [ -f "$STACKS_DIR/node-api.md" ] && STACK_RULES="${STACK_RULES}$(cat "$STACKS_DIR/node-api.md")"$'\n\n'; fi; [ -f "requirements.txt" ] || [ -f "pyproject.toml" ] && [ -f "$STACKS_DIR/python.md" ] && STACK_RULES="${STACK_RULES}$(cat "$STACKS_DIR/python.md")"$'\n\n'; [ -f "go.mod" ] && [ -f "$STACKS_DIR/go.md" ] && STACK_RULES="${STACK_RULES}$(cat "$STACKS_DIR/go.md")"$'\n\n'; [ -f "Cargo.toml" ] && [ -f "$STACKS_DIR/rust.md" ] && STACK_RULES="${STACK_RULES}$(cat "$STACKS_DIR/rust.md")"$'\n\n'; ([ -f ".gsd-t/contracts/design-contract.md" ] || [ -f "design-tokens.json" ] || [ -d "design-tokens" ] || [ -f ".figmarc" ] || [ -f "figma.config.json" ] || grep -q '"figma"' ~/.claude/settings.json 2>/dev/null) && [ -f "$STACKS_DIR/design-to-code.md" ] && STACK_RULES="${STACK_RULES}$(cat "$STACKS_DIR/design-to-code.md")"$'\n\n'; fi`
@@ -127,6 +147,10 @@ For each connection:
 
 ## Step 4: End-to-End Smoke Test
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-integrate --step 4 --step-label "End-to-End Smoke Test" 2>/dev/null || true
+```
+
 Run through the primary user flows:
 1. Identify the 3-5 most critical paths from requirements
 2. Trace each path through all domain boundaries
@@ -153,6 +177,10 @@ Result: PARTIAL — needs pagination contract addition
 
 ## Step 5: Contract Compliance Testing
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-integrate --step 5 --step-label "Contract Compliance Testing" 2>/dev/null || true
+```
+
 Spawn a QA subagent via the Task tool to verify contract compliance at all domain boundaries — `spawnType: 'validation'` (always headless, `--watch` ignored):
 
 ```
@@ -195,6 +223,10 @@ QA failure blocks integration completion.
 
 ## Step 6: Document Ripple
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-integrate --step 6 --step-label "Document Ripple" 2>/dev/null || true
+```
+
 Integration is where the real system takes shape. Verify documentation matches reality:
 
 ### Always update:
@@ -211,6 +243,10 @@ Integration is where the real system takes shape. Verify documentation matches r
 
 ## Step 7: Test Verification
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-integrate --step 7 --step-label "Test Verification" 2>/dev/null || true
+```
+
 After integration and doc ripple, verify everything works together:
 
 1. **Update tests**: Add or update integration tests for newly wired domain boundaries
@@ -225,6 +261,10 @@ After integration and doc ripple, verify everything works together:
 
 ## Step 7.5: Red Team — Adversarial QA (MANDATORY)
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-integrate --step 7 --step-label ".5: Red Team — Adversarial QA (MANDATORY)" 2>/dev/null || true
+```
+
 After integration tests pass, spawn an adversarial Red Team agent on the integrated system. Success is measured by bugs found, not tests passed.
 
 ⚙ [opus] Red Team → adversarial validation of integrated system
@@ -252,6 +292,10 @@ Append to `.gsd-t/token-log.md`:
 
 ## Step 8: Doc-Ripple (Automated)
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-integrate --step 8 --step-label "Doc-Ripple (Automated)" 2>/dev/null || true
+```
+
 After all integration work is committed but before reporting completion:
 
 1. Run threshold check — read `git diff --name-only HEAD~1` and evaluate against doc-ripple-contract.md trigger conditions
@@ -272,6 +316,10 @@ Report: 'Doc-ripple: {N} checked, {N} updated, {N} skipped'"
 
 ## Step 9: Handle Integration Issues
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-integrate --step 9 --step-label "Handle Integration Issues" 2>/dev/null || true
+```
+
 For each issue found:
 1. Determine if it's a contract gap (missing specification) or implementation bug
 2. **Contract gap**: Update the contract, create a follow-up task
@@ -280,6 +328,10 @@ For each issue found:
 
 ## Step 10: Update State
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-integrate --step 10 --step-label "Update State" 2>/dev/null || true
+```
+
 Update `.gsd-t/progress.md`:
 - Set status to `INTEGRATED`
 - Add contract audit results

package/commands/gsd-t-milestone.md

@@ -4,6 +4,10 @@ You are defining a new milestone for the project. A milestone is a significant d
 
 ## Step 1: Load Context
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-milestone --step 1 --step-label "Load Context" 2>/dev/null || true
+```
+
 Read:
 1. `CLAUDE.md`
 2. `.gsd-t/progress.md` — check if GSD-T is initialized
@@ -13,6 +17,10 @@ If `.gsd-t/` doesn't exist, run the init workflow first.
 
 ## Step 2: Define the Milestone
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-milestone --step 2 --step-label "Define the Milestone" 2>/dev/null || true
+```
+
 Based on $ARGUMENTS and available documentation:
 
 1. **Name**: Clear, descriptive milestone name
@@ -29,6 +37,10 @@ Update `.gsd-t/progress.md` milestones table:
 
 ## Step 3: Clear Previous Milestone State (if applicable)
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-milestone --step 3 --step-label "Clear Previous Milestone State (if applicable)" 2>/dev/null || true
+```
+
 If there's a completed previous milestone:
 1. Archive domain task files (they contain valuable context)
 2. Keep contracts that are still valid
@@ -40,6 +52,10 @@ Ask user: "Milestone {N-1} is still {status}. Archive it and start new? Or compl
 
 ## Step 4: Pre-Partition Assessment
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-milestone --step 4 --step-label "Pre-Partition Assessment" 2>/dev/null || true
+```
+
 Before formal partitioning, do a quick assessment:
 
 - **Complexity estimate**: Simple (1-2 domains), Medium (3-4), Complex (5+)
@@ -52,6 +68,10 @@ Present the assessment and ask: "Ready to partition into domains now, or want to
 
 ## Step 5: Document Ripple
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-milestone --step 5 --step-label "Document Ripple" 2>/dev/null || true
+```
+
 After defining the milestone, update affected documentation:
 
 ### Always update:
@@ -67,6 +87,10 @@ After defining the milestone, update affected documentation:
 
 ## Step 6: Test Verification
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-milestone --step 6 --step-label "Test Verification" 2>/dev/null || true
+```
+
 Before proceeding to partition:
 
 1. **Run existing tests**: Execute the full test suite to confirm the codebase is clean before starting the milestone
@@ -75,6 +99,10 @@ Before proceeding to partition:
 
 ## Step 7: Auto-Partition (if user confirms)
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-milestone --step 7 --step-label "Auto-Partition (if user confirms)" 2>/dev/null || true
+```
+
 If the user wants to proceed immediately, execute the partition workflow (same as gsd-t-partition) for this milestone.
 
 Otherwise, set status to DEFINED and remind them:

package/commands/gsd-t-partition.md

@@ -11,6 +11,10 @@ Per `.gsd-t/contracts/model-selection-contract.md` v1.0.0.
 
 ## Step 0.5: Scan Freshness Auto-Refresh
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-partition --step 0 --step-label ".5: Scan Freshness Auto-Refresh" 2>/dev/null || true
+```
+
 Before reading scan data, check if scan docs are stale and auto-refresh if needed. This ensures partition decisions are based on current code — no warnings, no user involvement.
 
 If `.gsd-t/scan/.cache.json` exists:
@@ -28,6 +32,10 @@ If `.gsd-t/scan/` doesn't exist at all → skip (no scan data to refresh).
 
 ## Step 1: Understand the Project
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-partition --step 1 --step-label "Understand the Project" 2>/dev/null || true
+```
+
 Read these files in order:
 1. `CLAUDE.md` — project conventions and context
 2. `.gsd-t/progress.md` — current state (if exists)
@@ -45,6 +53,10 @@ If `.gsd-t/` doesn't exist, create the full directory structure:
 
 ## Step 1.5: Assumption Audit (MANDATORY — complete before domain work begins)
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-partition --step 1 --step-label ".5: Assumption Audit (MANDATORY — complete before domain work begins)" 2>/dev/null || true
+```
+
 Before partitioning, surface and lock down all assumptions baked into the requirements. Unexamined assumptions become architectural decisions no one approved.
 
 Work through each category below. For every match found, write the explicit disposition into the affected domain's `constraints.md` and into the Decision Log in `.gsd-t/progress.md`.
@@ -102,6 +114,10 @@ For each ambiguous item:
 
 ## Step 1.55: Graph-Enhanced Boundary Detection (if available)
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-partition --step 1 --step-label ".55: Graph-Enhanced Boundary Detection (if available)" 2>/dev/null || true
+```
+
 If `.gsd-t/graph/meta.json` exists, query the graph to inform domain decomposition:
 
 1. **Entity-to-file mapping**: `query('getEntities', { file })` for each source file — understand what functions/classes exist where
@@ -114,6 +130,10 @@ Use graph results to **propose initial domain boundaries** based on actual code
 
 ## Step 1.6: Consumer Surface Identification (MANDATORY — complete before domain work)
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-partition --step 1 --step-label ".6: Consumer Surface Identification (MANDATORY — complete before domain work)" 2>/dev/null || true
+```
+
 Before decomposing into domains, identify **every surface that will consume this system**. A surface is any client, app, or integration that calls your backend — web app, mobile app, CLI, external API, admin panel, background job, etc.
 
 Skipping this step leads to duplicated backend logic when a second consumer is added later.
@@ -190,6 +210,10 @@ If SharedCore was created, populate `.gsd-t/contracts/shared-services-contract.m
 
 ## Step 2: Identify Domains
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-partition --step 2 --step-label "Identify Domains" 2>/dev/null || true
+```
+
 Decompose the milestone into 2-5 independent domains. Each domain should:
 - Own a distinct area of functionality
 - Have minimal overlap with other domains
@@ -239,6 +263,10 @@ For each domain, create `.gsd-t/domains/{domain-name}/`:
 
 ## Step 3: Write Contracts
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-partition --step 3 --step-label "Write Contracts" 2>/dev/null || true
+```
+
 Contracts define HOW domains interact. Create files in `.gsd-t/contracts/`:
 
 For each boundary between domains, write a contract:
@@ -299,6 +327,10 @@ Owner: ui domain
 
 ## Step 3.5: Design Brief Detection (UI Projects Only)
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-partition --step 3 --step-label ".5: Design Brief Detection (UI Projects Only)" 2>/dev/null || true
+```
+
 After writing contracts, check for UI/frontend signals. If found, generate `.gsd-t/contracts/design-brief.md` to give all subagents a consistent visual language reference.
 
 **Skip this step entirely if no UI signals are detected.**
@@ -380,6 +412,10 @@ Log in `.gsd-t/progress.md` Decision Log: `- {date}: Design brief generated at .
 
 ## Step 3.6: Design Contract Bootstrap (Figma/Design Reference Detection)
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-partition --step 3 --step-label ".6: Design Contract Bootstrap (Figma/Design Reference Detection)" 2>/dev/null || true
+```
+
 After the design brief, check whether this project has a design reference (Figma, images, prototypes). If found, create `.gsd-t/contracts/design-contract.md` to activate the design-to-code stack rule during execute.
 
 **Skip this step if `.gsd-t/contracts/design-contract.md` already exists.**
@@ -427,6 +463,10 @@ Log in `.gsd-t/progress.md` Decision Log: `- {date}: Design contract created at
 
 ## Step 4: Initialize Progress
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-partition --step 4 --step-label "Initialize Progress" 2>/dev/null || true
+```
+
 Write `.gsd-t/progress.md`:
 ```markdown
 # GSD-T Progress
@@ -454,6 +494,10 @@ Write `.gsd-t/progress.md`:
 
 ## Step 5: Document Ripple
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-partition --step 5 --step-label "Document Ripple" 2>/dev/null || true
+```
+
 After creating domains and contracts, update affected documentation:
 
 ### Always update:
@@ -468,6 +512,10 @@ After creating domains and contracts, update affected documentation:
 
 ## Step 6: Test Verification
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-partition --step 6 --step-label "Test Verification" 2>/dev/null || true
+```
+
 Before finalizing the partition:
 
 1. **Run existing tests**: Execute the full test suite to confirm codebase is clean before domain work begins
@@ -476,6 +524,10 @@ Before finalizing the partition:
 
 ## Step 7: Validate
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-partition --step 7 --step-label "Validate" 2>/dev/null || true
+```
+
 Before finishing, verify:
 - [ ] Every file in `src/` is owned by exactly one domain
 - [ ] No domain scope overlaps with another

package/commands/gsd-t-plan.md

@@ -11,6 +11,10 @@ Per `.gsd-t/contracts/model-selection-contract.md` v1.0.0.
 
 ## Step 1: Load Full Context
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-plan --step 1 --step-label "Load Full Context" 2>/dev/null || true
+```
+
 Read ALL of these:
 1. `CLAUDE.md`
 2. `.gsd-t/progress.md`
@@ -25,6 +29,10 @@ Read ALL of these:
 
 ## Step 1.5: Graph-Enhanced Dependency Detection
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-plan --step 1 --step-label ".5: Graph-Enhanced Dependency Detection" 2>/dev/null || true
+```
+
 If `.gsd-t/graph/meta.json` exists (graph index is available):
 1. Query `findDuplicates` to detect when planned tasks would create duplicate functions across domains — flag for SharedCore extraction or deduplication
 2. Query `getImporters` for key modules to identify implicit task dependencies that might not be obvious from contracts alone
@@ -34,6 +42,10 @@ If graph is not available, skip this step.
 
 ## Step 1.7: Pre-Mortem — Historical Failure Analysis
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-plan --step 1 --step-label ".7: Pre-Mortem — Historical Failure Analysis" 2>/dev/null || true
+```
+
 Before creating task lists, check historical task-metrics for domain-level failure patterns from previous milestones:
 
 1. Run via Bash:
@@ -52,6 +64,10 @@ Before creating task lists, check historical task-metrics for domain-level failu
 
 ## Step 2: Create Task Lists Per Domain
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-plan --step 2 --step-label "Create Task Lists Per Domain" 2>/dev/null || true
+```
+
 ### SharedCore-First Pre-Check
 
 Before writing any domain task lists:
@@ -258,6 +274,10 @@ After creating task lists, append a traceability table to `docs/requirements.md`
 
 ## Step 3: Map Cross-Domain Dependencies
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-plan --step 3 --step-label "Map Cross-Domain Dependencies" 2>/dev/null || true
+```
+
 Update `.gsd-t/contracts/integration-points.md` with the full dependency graph **and wave groupings**:
 
 ```markdown
@@ -325,6 +345,10 @@ Each wave contains domains/tasks that can safely run in parallel (no shared file
 
 ## Step 4: Estimate Scope
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-plan --step 4 --step-label "Estimate Scope" 2>/dev/null || true
+```
+
 Add to each domain's `tasks.md`:
 ```markdown
 ## Execution Estimate
@@ -336,6 +360,10 @@ Add to each domain's `tasks.md`:
 
 ## Step 5: Document Ripple
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-plan --step 5 --step-label "Document Ripple" 2>/dev/null || true
+```
+
 After creating task lists and mapping dependencies, update affected documentation:
 
 ### Always update:
@@ -351,6 +379,10 @@ After creating task lists and mapping dependencies, update affected documentatio
 
 ## Step 6: Test Verification
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-plan --step 6 --step-label "Test Verification" 2>/dev/null || true
+```
+
 Before finalizing the plan:
 
 1. **Run existing tests**: Execute the full test suite to confirm codebase state before execution begins
@@ -359,6 +391,10 @@ Before finalizing the plan:
 
 ## Step 7: Plan Validation
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-plan --step 7 --step-label "Plan Validation" 2>/dev/null || true
+```
+
 Spawn a Task subagent to validate the plan before proceeding:
 
 ```
@@ -393,6 +429,10 @@ If validation FAIL, append each gap to `.gsd-t/qa-issues.md` (create with header
 
 ## Step 8: Update Progress
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-plan --step 8 --step-label "Update Progress" 2>/dev/null || true
+```
+
 Update `.gsd-t/progress.md`:
 - Set status to `PLANNED`
 - Update domain table with task counts
@@ -400,6 +440,10 @@ Update `.gsd-t/progress.md`:
 
 ## Step 9: Report
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-plan --step 9 --step-label "Report" 2>/dev/null || true
+```
+
 ### Autonomy Behavior
 
 **Level 3 (Full Auto)**: Log a brief status line (e.g., "✅ Plan complete — {N} tasks across {N} domains, {execution mode}") and auto-advance to the next phase. Do NOT wait for user input.

package/commands/gsd-t-project.md

@@ -4,6 +4,10 @@ You are the lead agent taking a complete project vision and breaking it into a l
 
 ## Step 1: Gather Project Context
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-project --step 1 --step-label "Gather Project Context" 2>/dev/null || true
+```
+
 Read everything available:
 1. `CLAUDE.md` (if exists)
 2. `docs/` — any existing documentation
@@ -24,6 +28,10 @@ Do NOT proceed until you have enough context to make informed milestone decision
 
 ## Step 2: Identify the Full Scope
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-project --step 2 --step-label "Identify the Full Scope" 2>/dev/null || true
+```
+
 List ALL major capabilities the project needs. Group them into functional areas:
 
 ```markdown
@@ -66,6 +74,10 @@ Adjust these categories based on the actual project. Not every project needs all
 
 ## Step 3: Sequence into Milestones
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-project --step 3 --step-label "Sequence into Milestones" 2>/dev/null || true
+```
+
 Break functional areas into milestones following these principles:
 
 ### Sequencing Rules:
@@ -84,6 +96,10 @@ Break functional areas into milestones following these principles:
 
 ## Step 4: Write the Milestone Roadmap
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-project --step 4 --step-label "Write the Milestone Roadmap" 2>/dev/null || true
+```
+
 Create `.gsd-t/roadmap.md`:
 
 ```markdown
@@ -142,6 +158,10 @@ Create `.gsd-t/roadmap.md`:
 
 ## Step 5: Update Project State
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-project --step 5 --step-label "Update Project State" 2>/dev/null || true
+```
+
 Initialize or update `.gsd-t/progress.md`:
 
 ```markdown
@@ -168,6 +188,10 @@ Ensure `CLAUDE.md` exists and references the roadmap and tech stack.
 
 ## Step 6: Document Ripple
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-project --step 6 --step-label "Document Ripple" 2>/dev/null || true
+```
+
 After creating the roadmap and updating project state, verify all documentation is consistent:
 
 ### Always update:
@@ -185,6 +209,10 @@ After creating the roadmap and updating project state, verify all documentation
 
 ## Step 7: Test Verification
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-project --step 7 --step-label "Test Verification" 2>/dev/null || true
+```
+
 Before reporting to the user:
 
 1. **If existing code**: Run the full test suite to establish a baseline before milestone work begins
@@ -193,6 +221,10 @@ Before reporting to the user:
 
 ## Step 8: Report to User
 
+```bash
+node scripts/gsd-t-watch-state.js advance --agent-id "$GSD_T_AGENT_ID" --parent-id "${GSD_T_PARENT_AGENT_ID:-null}" --command gsd-t-project --step 8 --step-label "Report to User" 2>/dev/null || true
+```
+
 Present:
 1. The full milestone roadmap (summary view)
 2. Total milestone count and rough estimate