@undeemed/get-shit-done-codex 1.20.3 → 1.20.7

package/get-shit-done/workflows/map-codebase.md

@@ -90,17 +90,13 @@ Use Task tool with `subagent_type="gsd-codebase-mapper"`, `model="{mapper_model}
 
 **Agent 1: Tech Focus**
 
-Task tool parameters:
 ```
-subagent_type: "gsd-codebase-mapper"
-model: "{mapper_model}"
-run_in_background: true
-description: "Map codebase tech stack"
-```
-
-Prompt:
-```
-Focus: tech
+Task(
+  subagent_type="gsd-codebase-mapper",
+  model="{mapper_model}",
+  run_in_background=true,
+  description="Map codebase tech stack",
+  prompt="Focus: tech
 
 Analyze this codebase for technology stack and external integrations.
 
@@ -108,22 +104,19 @@ Write these documents to .planning/codebase/:
 - STACK.md - Languages, runtime, frameworks, dependencies, configuration
 - INTEGRATIONS.md - External APIs, databases, auth providers, webhooks
 
-Explore thoroughly. Write documents directly using templates. Return confirmation only.
+Explore thoroughly. Write documents directly using templates. Return confirmation only."
+)
 ```
 
 **Agent 2: Architecture Focus**
 
-Task tool parameters:
-```
-subagent_type: "gsd-codebase-mapper"
-model: "{mapper_model}"
-run_in_background: true
-description: "Map codebase architecture"
-```
-
-Prompt:
 ```
-Focus: arch
+Task(
+  subagent_type="gsd-codebase-mapper",
+  model="{mapper_model}",
+  run_in_background=true,
+  description="Map codebase architecture",
+  prompt="Focus: arch
 
 Analyze this codebase architecture and directory structure.
 
@@ -131,22 +124,19 @@ Write these documents to .planning/codebase/:
 - ARCHITECTURE.md - Pattern, layers, data flow, abstractions, entry points
 - STRUCTURE.md - Directory layout, key locations, naming conventions
 
-Explore thoroughly. Write documents directly using templates. Return confirmation only.
+Explore thoroughly. Write documents directly using templates. Return confirmation only."
+)
 ```
 
 **Agent 3: Quality Focus**
 
-Task tool parameters:
 ```
-subagent_type: "gsd-codebase-mapper"
-model: "{mapper_model}"
-run_in_background: true
-description: "Map codebase conventions"
-```
-
-Prompt:
-```
-Focus: quality
+Task(
+  subagent_type="gsd-codebase-mapper",
+  model="{mapper_model}",
+  run_in_background=true,
+  description="Map codebase conventions",
+  prompt="Focus: quality
 
 Analyze this codebase for coding conventions and testing patterns.
 
@@ -154,29 +144,27 @@ Write these documents to .planning/codebase/:
 - CONVENTIONS.md - Code style, naming, patterns, error handling
 - TESTING.md - Framework, structure, mocking, coverage
 
-Explore thoroughly. Write documents directly using templates. Return confirmation only.
+Explore thoroughly. Write documents directly using templates. Return confirmation only."
+)
 ```
 
 **Agent 4: Concerns Focus**
 
-Task tool parameters:
-```
-subagent_type: "gsd-codebase-mapper"
-model: "{mapper_model}"
-run_in_background: true
-description: "Map codebase concerns"
-```
-
-Prompt:
 ```
-Focus: concerns
+Task(
+  subagent_type="gsd-codebase-mapper",
+  model="{mapper_model}",
+  run_in_background=true,
+  description="Map codebase concerns",
+  prompt="Focus: concerns
 
 Analyze this codebase for technical debt, known issues, and areas of concern.
 
 Write this document to .planning/codebase/:
 - CONCERNS.md - Tech debt, bugs, security, performance, fragile areas
 
-Explore thoroughly. Write document directly using template. Return confirmation only.
+Explore thoroughly. Write document directly using template. Return confirmation only."
+)
 ```
 
 Continue to collect_confirmations.

package/get-shit-done/workflows/new-milestone.md

@@ -128,7 +128,9 @@ Focus ONLY on what's needed for the NEW features.
 
 <question>{QUESTION}</question>
 
-<project_context>[PROJECT.md summary]</project_context>
+<files_to_read>
+- .planning/PROJECT.md (Project context)
+</files_to_read>
 
 <downstream_consumer>{CONSUMER}</downstream_consumer>
 
@@ -157,7 +159,12 @@ After all 4 complete, spawn synthesizer:
 Task(prompt="
 Synthesize research outputs into SUMMARY.md.
 
-Read: .planning/research/STACK.md, FEATURES.md, ARCHITECTURE.md, PITFALLS.md
+<files_to_read>
+- .planning/research/STACK.md
+- .planning/research/FEATURES.md
+- .planning/research/ARCHITECTURE.md
+- .planning/research/PITFALLS.md
+</files_to_read>
 
 Write to: .planning/research/SUMMARY.md
 Use template: ~/.codex/get-shit-done/templates/research-project/SUMMARY.md
@@ -264,11 +271,13 @@ node ~/.codex/get-shit-done/bin/gsd-tools.cjs commit "docs: define milestone v[X
 ```
 Task(prompt="
 <planning_context>
-@.planning/PROJECT.md
-@.planning/REQUIREMENTS.md
-@.planning/research/SUMMARY.md (if exists)
-@.planning/config.json
-@.planning/MILESTONES.md
+<files_to_read>
+- .planning/PROJECT.md
+- .planning/REQUIREMENTS.md
+- .planning/research/SUMMARY.md (if exists)
+- .planning/config.json
+- .planning/MILESTONES.md
+</files_to_read>
 </planning_context>
 
 <instructions>

package/get-shit-done/workflows/new-project.md

@@ -49,7 +49,7 @@ The document should describe what you want to build.
 INIT=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs init new-project)
 ```
 
-Parse JSON for: `researcher_model`, `synthesizer_model`, `roadmapper_model`, `commit_docs`, `project_exists`, `has_codebase_map`, `planning_exists`, `has_existing_code`, `has_package_file`, `is_brownfield`, `needs_codebase_map`, `has_git`.
+Parse JSON for: `researcher_model`, `synthesizer_model`, `roadmapper_model`, `commit_docs`, `project_exists`, `has_codebase_map`, `planning_exists`, `has_existing_code`, `has_package_file`, `is_brownfield`, `needs_codebase_map`, `has_git`, `project_path`.
 
 **If `project_exists` is true:** Error — project already initialized. Use `/gsd:progress`.
 
@@ -176,7 +176,8 @@ Create `.planning/config.json` with mode set to "yolo":
   "workflow": {
     "research": true|false,
     "plan_check": true|false,
-    "verifier": true|false
+    "verifier": true|false,
+    "auto_advance": true
   }
 }
 ```
@@ -190,6 +191,12 @@ mkdir -p .planning
 node ~/.codex/get-shit-done/bin/gsd-tools.cjs commit "chore: add project config" --files .planning/config.json
 ```
 
+**Persist auto-advance to config (survives context compaction):**
+
+```bash
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs config-set workflow.auto_advance true
+```
+
 Proceed to Step 4 (skip Steps 3 and 5).
 
 ## 3. Deep Questioning
@@ -534,7 +541,7 @@ Display spawning indicator:
   → Pitfalls research
 ```
 
-Spawn 4 parallel gsd-project-researcher agents with rich context:
+Spawn 4 parallel gsd-project-researcher agents with path references:
 
 ```
 Task(prompt="First, read ~/.codex/agents/gsd-project-researcher.md for your role and instructions.
@@ -554,9 +561,9 @@ Subsequent: Research what's needed to add [target features] to an existing [doma
 What's the standard 2025 stack for [domain]?
 </question>
 
-<project_context>
-[PROJECT.md summary - core value, constraints, what they're building]
-</project_context>
+<files_to_read>
+- {project_path} (Project context and goals)
+</files_to_read>
 
 <downstream_consumer>
 Your STACK.md feeds into roadmap creation. Be prescriptive:
@@ -594,9 +601,9 @@ Subsequent: How do [target features] typically work? What's expected behavior?
 What features do [domain] products have? What's table stakes vs differentiating?
 </question>
 
-<project_context>
-[PROJECT.md summary]
-</project_context>
+<files_to_read>
+- {project_path} (Project context)
+</files_to_read>
 
 <downstream_consumer>
 Your FEATURES.md feeds into requirements definition. Categorize clearly:
@@ -634,9 +641,9 @@ Subsequent: How do [target features] integrate with existing [domain] architectu
 How are [domain] systems typically structured? What are major components?
 </question>
 
-<project_context>
-[PROJECT.md summary]
-</project_context>
+<files_to_read>
+- {project_path} (Project context)
+</files_to_read>
 
 <downstream_consumer>
 Your ARCHITECTURE.md informs phase structure in roadmap. Include:
@@ -674,9 +681,9 @@ Subsequent: What are common mistakes when adding [target features] to [domain]?
 What do [domain] projects commonly get wrong? Critical mistakes?
 </question>
 
-<project_context>
-[PROJECT.md summary]
-</project_context>
+<files_to_read>
+- {project_path} (Project context)
+</files_to_read>
 
 <downstream_consumer>
 Your PITFALLS.md prevents mistakes in roadmap/planning. For each pitfall:
@@ -706,13 +713,12 @@ Task(prompt="
 Synthesize research outputs into SUMMARY.md.
 </task>
 
-<research_files>
-Read these files:
+<files_to_read>
 - .planning/research/STACK.md
 - .planning/research/FEATURES.md
 - .planning/research/ARCHITECTURE.md
 - .planning/research/PITFALLS.md
-</research_files>
+</files_to_read>
 
 <output>
 Write to: .planning/research/SUMMARY.md
@@ -895,23 +901,18 @@ Display stage banner:
 ◆ Spawning roadmapper...
 ```
 
-Spawn gsd-roadmapper agent with context:
+Spawn gsd-roadmapper agent with path references:
 
 ```
 Task(prompt="
 <planning_context>
 
-**Project:**
-@.planning/PROJECT.md
-
-**Requirements:**
-@.planning/REQUIREMENTS.md
-
-**Research (if exists):**
-@.planning/research/SUMMARY.md
-
-**Config:**
-@.planning/config.json
+<files_to_read>
+- .planning/PROJECT.md (Project context)
+- .planning/REQUIREMENTS.md (v1 Requirements)
+- .planning/research/SUMMARY.md (Research findings - if exists)
+- .planning/config.json (Depth and mode settings)
+</files_to_read>
 
 </planning_context>
 
@@ -999,7 +1000,9 @@ Use AskUserQuestion:
   User feedback on roadmap:
   [user's notes]
 
-  Current ROADMAP.md: @.planning/ROADMAP.md
+  <files_to_read>
+  - .planning/ROADMAP.md (Current roadmap to revise)
+  </files_to_read>
 
   Update the roadmap based on feedback. Edit files in place.
   Return ROADMAP REVISED with changes made.

package/get-shit-done/workflows/plan-milestone-gaps.md

@@ -123,19 +123,34 @@ Add new phases to current milestone:
 ...
 ```
 
-## 7. Create Phase Directories
+## 7. Update REQUIREMENTS.md Traceability Table (REQUIRED)
+
+For each REQ-ID assigned to a gap closure phase:
+- Update the Phase column to reflect the new gap closure phase
+- Reset Status to `Pending`
+
+Reset checked-off requirements the audit found unsatisfied:
+- Change `[x]` → `[ ]` for any requirement marked unsatisfied in the audit
+- Update coverage count at top of REQUIREMENTS.md
+
+```bash
+# Verify traceability table reflects gap closure assignments
+grep -c "Pending" .planning/REQUIREMENTS.md
+```
+
+## 8. Create Phase Directories
 
 ```bash
 mkdir -p ".planning/phases/{NN}-{name}"
 ```
 
-## 8. Commit Roadmap Update
+## 9. Commit Roadmap and Requirements Update
 
 ```bash
-node ~/.codex/get-shit-done/bin/gsd-tools.cjs commit "docs(roadmap): add gap closure phases {N}-{M}" --files .planning/ROADMAP.md
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs commit "docs(roadmap): add gap closure phases {N}-{M}" --files .planning/ROADMAP.md .planning/REQUIREMENTS.md
 ```
 
-## 9. Offer Next Steps
+## 10. Offer Next Steps
 
 ```markdown
 ## ✓ Gap Closure Phases Created
@@ -250,7 +265,10 @@ becomes:
 - [ ] Gaps grouped into logical phases
 - [ ] User confirmed phase plan
 - [ ] ROADMAP.md updated with new phases
+- [ ] REQUIREMENTS.md traceability table updated with gap closure phase assignments
+- [ ] Unsatisfied requirement checkboxes reset (`[x]` → `[ ]`)
+- [ ] Coverage count updated in REQUIREMENTS.md
 - [ ] Phase directories created
-- [ ] Changes committed
+- [ ] Changes committed (includes REQUIREMENTS.md)
 - [ ] User knows to run `/gsd:plan-phase` next
 </success_criteria>

package/get-shit-done/workflows/plan-phase.md

@@ -12,23 +12,15 @@ Read all files referenced by the invoking prompt's execution_context before star
 
 ## 1. Initialize
 
-Load all context in one call (include file contents to avoid redundant reads):
+Load all context in one call (paths only to minimize orchestrator context):
 
 ```bash
-INIT_RAW=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs init plan-phase "$PHASE" --include state,roadmap,requirements,context,research,verification,uat)
-# Large payloads are written to a tmpfile — output starts with @file:/path
-if [[ "$INIT_RAW" == @file:* ]]; then
-  INIT_FILE="${INIT_RAW#@file:}"
-  INIT=$(cat "$INIT_FILE")
-  rm -f "$INIT_FILE"
-else
-  INIT="$INIT_RAW"
-fi
+INIT=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs init plan-phase "$PHASE")
 ```
 
-Parse JSON for: `researcher_model`, `planner_model`, `checker_model`, `research_enabled`, `plan_checker_enabled`, `commit_docs`, `phase_found`, `phase_dir`, `phase_number`, `phase_name`, `phase_slug`, `padded_phase`, `has_research`, `has_context`, `has_plans`, `plan_count`, `planning_exists`, `roadmap_exists`.
+Parse JSON for: `researcher_model`, `planner_model`, `checker_model`, `research_enabled`, `plan_checker_enabled`, `nyquist_validation_enabled`, `commit_docs`, `phase_found`, `phase_dir`, `phase_number`, `phase_name`, `phase_slug`, `padded_phase`, `has_research`, `has_context`, `has_plans`, `plan_count`, `planning_exists`, `roadmap_exists`.
 
-**File contents (from --include):** `state_content`, `roadmap_content`, `requirements_content`, `context_content`, `research_content`, `verification_content`, `uat_content`. These are null if files don't exist.
+**File paths (for <files_to_read> blocks):** `state_path`, `roadmap_path`, `requirements_path`, `context_path`, `research_path`, `verification_path`, `uat_path`. These are null if files don't exist.
 
 **If `planning_exists` is false:** Error — run `/gsd:new-project` first.
 
@@ -55,13 +47,11 @@ PHASE_INFO=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs roadmap get-phase "${
 
 ## 4. Load CONTEXT.md
 
-Use `context_content` from init JSON (already loaded via `--include context`).
+Check `context_path` from init JSON.
 
-**CRITICAL:** Use `context_content` from INIT — pass to researcher, planner, checker, and revision agents.
+If `context_path` is not null, display: `Using phase context from: ${context_path}`
 
-If `context_content` is not null, display: `Using phase context from: ${PHASE_DIR}/*-CONTEXT.md`
-
-**If `context_content` is null (no CONTEXT.md exists):**
+**If `context_path` is null (no CONTEXT.md exists):**
 
 Use AskUserQuestion:
 - header: "No context"
@@ -94,10 +84,7 @@ Display banner:
 
 ```bash
 PHASE_DESC=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs roadmap get-phase "${PHASE}" | jq -r '.section')
-# Use requirements_content from INIT (already loaded via --include requirements)
-REQUIREMENTS=$(echo "$INIT" | jq -r '.requirements_content // empty' | grep -A100 "## Requirements" | head -50)
-STATE_SNAP=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs state-snapshot)
-# Extract decisions from state-snapshot JSON: jq '.decisions[] | "\(.phase): \(.summary) - \(.rationale)"'
+PHASE_REQ_IDS=$(node ~/.codex/get-shit-done/bin/gsd-tools.cjs roadmap get-phase "${PHASE}" | jq -r '.section // empty' | grep -i "Requirements:" | head -1 | sed 's/.*Requirements:\*\*\s*//' | sed 's/[\[\]]//g' | tr ',' '\n' | sed 's/^ *//;s/ *$//' | grep -v '^$' | tr '\n' ',' | sed 's/,$//')
 ```
 
 Research prompt:
@@ -108,19 +95,18 @@ Research how to implement Phase {phase_number}: {phase_name}
 Answer: "What do I need to know to PLAN this phase well?"
 </objective>
 
-<phase_context>
-IMPORTANT: If CONTEXT.md exists below, it contains user decisions from /gsd:discuss-phase.
-- **Decisions** = Locked — research THESE deeply, no alternatives
-- **Codex's Discretion** = Freedom areas — research options, recommend
-- **Deferred Ideas** = Out of scope — ignore
-
-{context_content}
-</phase_context>
+<files_to_read>
+- {context_path} (USER DECISIONS from /gsd:discuss-phase)
+- {requirements_path} (Project requirements)
+- {state_path} (Project decisions and history)
+</files_to_read>
 
 <additional_context>
 **Phase description:** {phase_description}
-**Requirements:** {requirements}
-**Prior decisions:** {decisions}
+**Phase requirement IDs (MUST address):** {phase_req_ids}
+
+**Project instructions:** Read ./CODEX.md if exists — follow project-specific guidelines
+**Project skills:** Check .agents/skills/ directory (if exists) — read SKILL.md files, research should account for project skill patterns
 </additional_context>
 
 <output>
@@ -142,6 +128,31 @@ Task(
 - **`## RESEARCH COMPLETE`:** Display confirmation, continue to step 6
 - **`## RESEARCH BLOCKED`:** Display blocker, offer: 1) Provide context, 2) Skip research, 3) Abort
 
+## 5.5. Create Validation Strategy (if Nyquist enabled)
+
+**Skip if:** `nyquist_validation_enabled` is false from INIT JSON.
+
+After researcher completes, check if RESEARCH.md contains a Validation Architecture section:
+
+```bash
+grep -l "## Validation Architecture" "${PHASE_DIR}"/*-RESEARCH.md 2>/dev/null
+```
+
+**If found:**
+1. Read validation template from `~/.codex/get-shit-done/templates/VALIDATION.md`
+2. Write to `${PHASE_DIR}/${PADDED_PHASE}-VALIDATION.md`
+3. Fill frontmatter: replace `{N}` with phase number, `{phase-slug}` with phase slug, `{date}` with current date
+4. If `commit_docs` is true:
+```bash
+node ~/.codex/get-shit-done/bin/gsd-tools.cjs commit-docs "docs(phase-${PHASE}): add validation strategy"
+```
+
+**If not found (and nyquist enabled):** Display warning:
+```
+⚠ Nyquist validation enabled but researcher did not produce a Validation Architecture section.
+  Continuing without validation strategy. Plans may fail Dimension 8 check.
+```
+
 ## 6. Check Existing Plans
 
 ```bash
@@ -150,19 +161,18 @@ ls "${PHASE_DIR}"/*-PLAN.md 2>/dev/null
 
 **If exists:** Offer: 1) Add more plans, 2) View existing, 3) Replan from scratch.
 
-## 7. Use Context Files from INIT
+## 7. Use Context Paths from INIT
 
-All file contents are already loaded via `--include` in step 1 (`@` syntax doesn't work across Task() boundaries):
+Extract from INIT JSON:
 
 ```bash
-# Extract from INIT JSON (no need to re-read files)
-STATE_CONTENT=$(echo "$INIT" | jq -r '.state_content // empty')
-ROADMAP_CONTENT=$(echo "$INIT" | jq -r '.roadmap_content // empty')
-REQUIREMENTS_CONTENT=$(echo "$INIT" | jq -r '.requirements_content // empty')
-RESEARCH_CONTENT=$(echo "$INIT" | jq -r '.research_content // empty')
-VERIFICATION_CONTENT=$(echo "$INIT" | jq -r '.verification_content // empty')
-UAT_CONTENT=$(echo "$INIT" | jq -r '.uat_content // empty')
-CONTEXT_CONTENT=$(echo "$INIT" | jq -r '.context_content // empty')
+STATE_PATH=$(echo "$INIT" | jq -r '.state_path // empty')
+ROADMAP_PATH=$(echo "$INIT" | jq -r '.roadmap_path // empty')
+REQUIREMENTS_PATH=$(echo "$INIT" | jq -r '.requirements_path // empty')
+RESEARCH_PATH=$(echo "$INIT" | jq -r '.research_path // empty')
+VERIFICATION_PATH=$(echo "$INIT" | jq -r '.verification_path // empty')
+UAT_PATH=$(echo "$INIT" | jq -r '.uat_path // empty')
+CONTEXT_PATH=$(echo "$INIT" | jq -r '.context_path // empty')
 ```
 
 ## 8. Spawn gsd-planner Agent
@@ -183,20 +193,20 @@ Planner prompt:
 **Phase:** {phase_number}
 **Mode:** {standard | gap_closure}
 
-**Project State:** {state_content}
-**Roadmap:** {roadmap_content}
-**Requirements:** {requirements_content}
+<files_to_read>
+- {state_path} (Project State)
+- {roadmap_path} (Roadmap)
+- {requirements_path} (Requirements)
+- {context_path} (USER DECISIONS from /gsd:discuss-phase)
+- {research_path} (Technical Research)
+- {verification_path} (Verification Gaps - if --gaps)
+- {uat_path} (UAT Gaps - if --gaps)
+</files_to_read>
 
-**Phase Context:**
-IMPORTANT: If context exists below, it contains USER DECISIONS from /gsd:discuss-phase.
-- **Decisions** = LOCKED — honor exactly, do not revisit
-- **Codex's Discretion** = Freedom — make implementation choices
-- **Deferred Ideas** = Out of scope — do NOT include
+**Phase requirement IDs (every ID MUST appear in a plan's `requirements` field):** {phase_req_ids}
 
-{context_content}
-
-**Research:** {research_content}
-**Gap Closure (if --gaps):** {verification_content} {uat_content}
+**Project instructions:** Read ./CODEX.md if exists — follow project-specific guidelines
+**Project skills:** Check .agents/skills/ directory (if exists) — read SKILL.md files, plans should account for project skill rules
 </planning_context>
 
 <downstream_consumer>
@@ -243,10 +253,6 @@ Display banner:
 ◆ Spawning plan checker...
 ```
 
-```bash
-PLANS_CONTENT=$(cat "${PHASE_DIR}"/*-PLAN.md 2>/dev/null)
-```
-
 Checker prompt:
 
 ```markdown
@@ -254,16 +260,18 @@ Checker prompt:
 **Phase:** {phase_number}
 **Phase Goal:** {goal from ROADMAP}
 
-**Plans to verify:** {plans_content}
-**Requirements:** {requirements_content}
+<files_to_read>
+- {PHASE_DIR}/*-PLAN.md (Plans to verify)
+- {roadmap_path} (Roadmap)
+- {requirements_path} (Requirements)
+- {context_path} (USER DECISIONS from /gsd:discuss-phase)
+- {research_path} (Technical Research — includes Validation Architecture)
+</files_to_read>
 
-**Phase Context:**
-IMPORTANT: Plans MUST honor user decisions. Flag as issue if plans contradict.
-- **Decisions** = LOCKED — plans must implement exactly
-- **Codex's Discretion** = Freedom areas — plans can choose approach
-- **Deferred Ideas** = Out of scope — plans must NOT include
+**Phase requirement IDs (MUST ALL be covered):** {phase_req_ids}
 
-{context_content}
+**Project instructions:** Read ./CODEX.md if exists — verify plans honor project guidelines
+**Project skills:** Check .agents/skills/ directory (if exists) — verify plans account for project skill rules
 </verification_context>
 
 <expected_output>
@@ -294,10 +302,6 @@ Track `iteration_count` (starts at 1 after initial plan + check).
 
 Display: `Sending back to planner for revision... (iteration {N}/3)`
 
-```bash
-PLANS_CONTENT=$(cat "${PHASE_DIR}"/*-PLAN.md 2>/dev/null)
-```
-
 Revision prompt:
 
 ```markdown
@@ -305,12 +309,12 @@ Revision prompt:
 **Phase:** {phase_number}
 **Mode:** revision
 
-**Existing plans:** {plans_content}
-**Checker issues:** {structured_issues_from_checker}
+<files_to_read>
+- {PHASE_DIR}/*-PLAN.md (Existing plans)
+- {context_path} (USER DECISIONS from /gsd:discuss-phase)
+</files_to_read>
 
-**Phase Context:**
-Revisions MUST still honor user decisions.
-{context_content}
+**Checker issues:** {structured_issues_from_checker}
 </revision_context>
 
 <instructions>
@@ -362,10 +366,36 @@ Display banner:
 Plans ready. Spawning execute-phase...
 ```
 
-Spawn execute-phase as Task:
+Spawn execute-phase as Task with direct workflow file reference (do NOT use Skill tool — Skills don't resolve inside Task subagents):
 ```
 Task(
-  prompt="Run /gsd:execute-phase ${PHASE}",
+  prompt="
+    <objective>
+    You are the execute-phase orchestrator. Execute all plans for Phase ${PHASE}: ${PHASE_NAME}.
+    </objective>
+
+    <execution_context>
+    @~/.codex/get-shit-done/workflows/execute-phase.md
+    @~/.codex/get-shit-done/references/checkpoints.md
+    @~/.codex/get-shit-done/references/tdd.md
+    @~/.codex/get-shit-done/references/model-profile-resolution.md
+    </execution_context>
+
+    <arguments>
+    PHASE=${PHASE}
+    ARGUMENTS='${PHASE} --auto --no-transition'
+    </arguments>
+
+    <instructions>
+    1. Read execute-phase.md from execution_context for your complete workflow
+    2. Follow ALL steps: initialize, handle_branching, validate_phase, discover_and_group_plans, execute_waves, aggregate_results, close_parent_artifacts, verify_phase_goal, update_roadmap
+    3. The --no-transition flag means: after verification + roadmap update, STOP and return status. Do NOT run transition.md.
+    4. When spawning executor agents, use subagent_type='gsd-executor' with the existing @file pattern from the workflow
+    5. When spawning verifier agents, use subagent_type='gsd-verifier'
+    6. Preserve the classifyHandoffIfNeeded workaround (spot-check on that specific error)
+    7. Do NOT use the Skill tool or /gsd: commands
+    </instructions>
+  ",
   subagent_type="general-purpose",
   description="Execute Phase ${PHASE}"
 )