@gordon.gan/specflow 1.0.0

package/prompts/build/phase-b-execute.md

@@ -0,0 +1,276 @@
+> **HARD GATE**: Wait for user confirmation after each task's review. Do NOT proceed to the next task until both spec compliance and code quality reviews pass and the user confirms.
+
+<!-- SOURCE: skills/subagent-driven-development/SKILL.md -->
+
+# Subagent-Driven Development (Phase B)
+
+Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.
+
+**Why subagents:** You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history -- you construct exactly what they need. This also preserves your own context for coordination work.
+
+**Core principle:** Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration
+
+## When to Use
+
+```dot
+digraph when_to_use {
+    "Have implementation plan?" [shape=diamond];
+    "Tasks mostly independent?" [shape=diamond];
+    "Stay in this session?" [shape=diamond];
+    "specflow:build Phase B" [shape=box];
+    "specflow:build Phase B (inline mode)" [shape=box];
+    "Manual execution or brainstorm first" [shape=box];
+
+    "Have implementation plan?" -> "Tasks mostly independent?" [label="yes"];
+    "Have implementation plan?" -> "Manual execution or brainstorm first" [label="no"];
+    "Tasks mostly independent?" -> "Stay in this session?" [label="yes"];
+    "Tasks mostly independent?" -> "Manual execution or brainstorm first" [label="no - tightly coupled"];
+    "Stay in this session?" -> "specflow:build Phase B" [label="yes"];
+    "Stay in this session?" -> "specflow:build Phase B (inline mode)" [label="no - parallel session"];
+}
+```
+
+**vs. Inline Mode (parallel session):**
+- Same session (no context switch)
+- Fresh subagent per task (no context pollution)
+- Two-stage review after each task: spec compliance first, then code quality
+- Faster iteration (no human-in-loop between tasks)
+
+## The Process
+
+```dot
+digraph process {
+    rankdir=TB;
+
+    subgraph cluster_per_task {
+        label="Per Task";
+        "Dispatch implementer subagent\n(Read .claude/specflow/prompts/shared/implementer-prompt.md)" [shape=box];
+        "Implementer subagent asks questions?" [shape=diamond];
+        "Answer questions, provide context" [shape=box];
+        "Implementer subagent implements, tests, commits, self-reviews" [shape=box];
+        "Dispatch spec reviewer subagent\n(Read .claude/specflow/prompts/shared/spec-reviewer-prompt.md)" [shape=box];
+        "Spec reviewer subagent confirms code matches spec?" [shape=diamond];
+        "Implementer subagent fixes spec gaps" [shape=box];
+        "Dispatch code quality reviewer subagent\n(Read .claude/specflow/prompts/shared/code-reviewer-prompt.md)" [shape=box];
+        "Code quality reviewer subagent approves?" [shape=diamond];
+        "Implementer subagent fixes quality issues" [shape=box];
+        "Mark task complete in TodoWrite" [shape=box];
+    }
+
+    "Read plan, extract all tasks with full text, note context, create TodoWrite" [shape=box];
+    "More tasks remain?" [shape=diamond];
+    "Dispatch final code reviewer subagent for entire implementation" [shape=box];
+    "Use specflow:done" [shape=box style=filled fillcolor=lightgreen];
+
+    "Read plan, extract all tasks with full text, note context, create TodoWrite" -> "Dispatch implementer subagent\n(Read .claude/specflow/prompts/shared/implementer-prompt.md)";
+    "Dispatch implementer subagent\n(Read .claude/specflow/prompts/shared/implementer-prompt.md)" -> "Implementer subagent asks questions?";
+    "Implementer subagent asks questions?" -> "Answer questions, provide context" [label="yes"];
+    "Answer questions, provide context" -> "Dispatch implementer subagent\n(Read .claude/specflow/prompts/shared/implementer-prompt.md)";
+    "Implementer subagent asks questions?" -> "Implementer subagent implements, tests, commits, self-reviews" [label="no"];
+    "Implementer subagent implements, tests, commits, self-reviews" -> "Dispatch spec reviewer subagent\n(Read .claude/specflow/prompts/shared/spec-reviewer-prompt.md)";
+    "Dispatch spec reviewer subagent\n(Read .claude/specflow/prompts/shared/spec-reviewer-prompt.md)" -> "Spec reviewer subagent confirms code matches spec?";
+    "Spec reviewer subagent confirms code matches spec?" -> "Implementer subagent fixes spec gaps" [label="no"];
+    "Implementer subagent fixes spec gaps" -> "Dispatch spec reviewer subagent\n(Read .claude/specflow/prompts/shared/spec-reviewer-prompt.md)" [label="re-review"];
+    "Spec reviewer subagent confirms code matches spec?" -> "Dispatch code quality reviewer subagent\n(Read .claude/specflow/prompts/shared/code-reviewer-prompt.md)" [label="yes"];
+    "Dispatch code quality reviewer subagent\n(Read .claude/specflow/prompts/shared/code-reviewer-prompt.md)" -> "Code quality reviewer subagent approves?";
+    "Code quality reviewer subagent approves?" -> "Implementer subagent fixes quality issues" [label="no"];
+    "Implementer subagent fixes quality issues" -> "Dispatch code quality reviewer subagent\n(Read .claude/specflow/prompts/shared/code-reviewer-prompt.md)" [label="re-review"];
+    "Code quality reviewer subagent approves?" -> "Mark task complete in TodoWrite" [label="yes"];
+    "Mark task complete in TodoWrite" -> "More tasks remain?";
+    "More tasks remain?" -> "Dispatch implementer subagent\n(Read .claude/specflow/prompts/shared/implementer-prompt.md)" [label="yes"];
+    "More tasks remain?" -> "Dispatch final code reviewer subagent for entire implementation" [label="no"];
+    "Dispatch final code reviewer subagent for entire implementation" -> "Use specflow:done";
+}
+```
+
+## Model Selection
+
+Use the least powerful model that can handle each role to conserve cost and increase speed.
+
+**Mechanical implementation tasks** (isolated functions, clear specs, 1-2 files): use a fast, cheap model. Most implementation tasks are mechanical when the plan is well-specified.
+
+**Integration and judgment tasks** (multi-file coordination, pattern matching, debugging): use a standard model.
+
+**Architecture, design, and review tasks**: use the most capable available model.
+
+**Task complexity signals:**
+- Touches 1-2 files with a complete spec -> cheap model
+- Touches multiple files with integration concerns -> standard model
+- Requires design judgment or broad codebase understanding -> most capable model
+
+## Handling Implementer Status
+
+Implementer subagents report one of four statuses. Handle each appropriately:
+
+**DONE:** Proceed to spec compliance review.
+
+**DONE_WITH_CONCERNS:** The implementer completed the work but flagged doubts. Read the concerns before proceeding. If the concerns are about correctness or scope, address them before review. If they're observations (e.g., "this file is getting large"), note them and proceed to review.
+
+**NEEDS_CONTEXT:** The implementer needs information that wasn't provided. Provide the missing context and re-dispatch.
+
+**BLOCKED:** The implementer cannot complete the task. Assess the blocker:
+1. If it's a context problem, provide more context and re-dispatch with the same model
+2. If the task requires more reasoning, re-dispatch with a more capable model
+3. If the task is too large, break it into smaller pieces
+4. If the plan itself is wrong, escalate to the human
+
+**Never** ignore an escalation or force the same model to retry without changes. If the implementer said it's stuck, something needs to change.
+
+## Prompt Templates
+
+- Read `.claude/specflow/prompts/shared/implementer-prompt.md` - Dispatch implementer subagent
+- Read `.claude/specflow/prompts/shared/spec-reviewer-prompt.md` - Dispatch spec compliance reviewer subagent
+- Read `.claude/specflow/prompts/shared/code-reviewer-prompt.md` - Dispatch code quality reviewer subagent
+
+## Example Workflow
+
+```
+You: I'm using specflow:build Phase B to execute this plan.
+
+[Read plan file once: specflow/changes/<change-name>/tasks.md]
+[Extract all 5 tasks with full text and context]
+[Create TodoWrite with all tasks]
+
+Task 1: Hook installation script
+
+[Get Task 1 text and context (already extracted)]
+[Dispatch implementation subagent with full task text + context]
+
+Implementer: "Before I begin - should the hook be installed at user or system level?"
+
+You: "User level (~/.config/specflow/hooks/)"
+
+Implementer: "Got it. Implementing now..."
+[Later] Implementer:
+  - Implemented install-hook command
+  - Added tests, 5/5 passing
+  - Self-review: Found I missed --force flag, added it
+  - Committed
+
+[Dispatch spec compliance reviewer]
+Spec reviewer: Spec compliant - all requirements met, nothing extra
+
+[Get git SHAs, dispatch code quality reviewer]
+Code reviewer: Strengths: Good test coverage, clean. Issues: None. Approved.
+
+[Mark Task 1 complete]
+
+Task 2: Recovery modes
+
+[Get Task 2 text and context (already extracted)]
+[Dispatch implementation subagent with full task text + context]
+
+Implementer: [No questions, proceeds]
+Implementer:
+  - Added verify/repair modes
+  - 8/8 tests passing
+  - Self-review: All good
+  - Committed
+
+[Dispatch spec compliance reviewer]
+Spec reviewer: Issues:
+  - Missing: Progress reporting (spec says "report every 100 items")
+  - Extra: Added --json flag (not requested)
+
+[Implementer fixes issues]
+Implementer: Removed --json flag, added progress reporting
+
+[Spec reviewer reviews again]
+Spec reviewer: Spec compliant now
+
+[Dispatch code quality reviewer]
+Code reviewer: Strengths: Solid. Issues (Important): Magic number (100)
+
+[Implementer fixes]
+Implementer: Extracted PROGRESS_INTERVAL constant
+
+[Code reviewer reviews again]
+Code reviewer: Approved
+
+[Mark Task 2 complete]
+
+...
+
+[After all tasks]
+[Dispatch final code-reviewer]
+Final reviewer: All requirements met, ready to merge
+
+Done!
+```
+
+## Advantages
+
+**vs. Manual execution:**
+- Subagents follow TDD naturally
+- Fresh context per task (no confusion)
+- Parallel-safe (subagents don't interfere)
+- Subagent can ask questions (before AND during work)
+
+**vs. Inline Mode:**
+- Same session (no handoff)
+- Continuous progress (no waiting)
+- Review checkpoints automatic
+
+**Efficiency gains:**
+- No file reading overhead (controller provides full text)
+- Controller curates exactly what context is needed
+- Subagent gets complete information upfront
+- Questions surfaced before work begins (not after)
+
+**Quality gates:**
+- Self-review catches issues before handoff
+- Two-stage review: spec compliance, then code quality
+- Review loops ensure fixes actually work
+- Spec compliance prevents over/under-building
+- Code quality ensures implementation is well-built
+
+**Cost:**
+- More subagent invocations (implementer + 2 reviewers per task)
+- Controller does more prep work (extracting all tasks upfront)
+- Review loops add iterations
+- But catches issues early (cheaper than debugging later)
+
+## Red Flags
+
+**Never:**
+- Start implementation on main/master branch without explicit user consent
+- Skip reviews (spec compliance OR code quality)
+- Proceed with unfixed issues
+- Dispatch multiple implementation subagents in parallel (conflicts)
+- Make subagent read plan file (provide full text instead)
+- Skip scene-setting context (subagent needs to understand where task fits)
+- Ignore subagent questions (answer before letting them proceed)
+- Accept "close enough" on spec compliance (spec reviewer found issues = not done)
+- Skip review loops (reviewer found issues = implementer fixes = review again)
+- Let implementer self-review replace actual review (both are needed)
+- **Start code quality review before spec compliance passes** (wrong order)
+- Move to next task while either review has open issues
+
+**If subagent asks questions:**
+- Answer clearly and completely
+- Provide additional context if needed
+- Don't rush them into implementation
+
+**If reviewer finds issues:**
+- Implementer (same subagent) fixes them
+- Reviewer reviews again
+- Repeat until approved
+- Don't skip the re-review
+
+**If subagent fails task:**
+- Dispatch fix subagent with specific instructions
+- Don't try to fix manually (context pollution)
+
+## Integration
+
+**Required workflow skills:**
+- **specflow:build Phase B (worktree)** - REQUIRED: Set up isolated workspace before starting
+- **specflow:build Phase A** - Creates the plan this skill executes
+- **specflow:review** - Code review template for reviewer subagents
+- **specflow:done** - Complete development after all tasks
+
+**Subagents should use:**
+- **specflow:build TDD** - Subagents follow TDD for each task
+
+**Alternative workflow:**
+- **specflow:build Phase B (inline mode)** - Use for parallel session instead of same-session execution

package/prompts/build/phase-b-review.md

@@ -0,0 +1,119 @@
+> **HARD GATE**: Spec compliance must pass before code quality review. Do NOT start code quality review until the spec reviewer has approved. Running them in parallel or out of order is forbidden.
+
+# Two-Phase Review Routing
+
+Orchestration for the two-phase review process used during specflow:build Phase B. Each task's implementation goes through spec compliance first, then code quality.
+
+## Overview
+
+Two sequential review phases ensure that code both matches the specification and meets quality standards. The order is non-negotiable: spec compliance first, code quality second.
+
+**Why this order:** Code quality review on spec-noncompliant code is wasted effort. Fix what's wrong before polishing how it's built.
+
+## Phase 1: Spec Compliance Review
+
+**Prompt source:** Read `.claude/specflow/prompts/shared/spec-reviewer-prompt.md`
+
+**Purpose:** Verify the implementer built what was requested -- nothing more, nothing less.
+
+**Dispatch:**
+```
+Task tool (general-purpose):
+  description: "Review spec compliance for Task N"
+  prompt: [content from spec-reviewer-prompt.md with placeholders filled]
+```
+
+**Inputs to provide:**
+- Full text of the task requirements (from the plan)
+- Implementer's report of what they claim they built
+- File paths of changed files
+
+**Expected output:**
+- Spec compliant (all requirements met, nothing extra)
+- OR: Issues found (list of missing/extra/misunderstood items with file:line references)
+
+**If issues found:**
+1. Send issues back to the implementer subagent for fixes
+2. Re-dispatch spec reviewer after fixes
+3. Repeat until spec compliance passes
+4. Only THEN proceed to Phase 2
+
+## Phase 2: Code Quality Review
+
+**Prompt source:** Read the `ReviewerFile` session context set after Stage B1b. Mapping details live in `.claude/specflow/prompts/build/language-router.md`. When `Language` is `unknown`, fall back to `.claude/specflow/prompts/shared/code-reviewer-prompt.md`.
+
+**Purpose:** Verify the implementation is well-built -- clean, tested, maintainable, and language-appropriate when an ECC reviewer is selected.
+
+**Dispatch:**
+```
+Task tool (general-purpose):
+  description: "Review code quality for Task N"
+  prompt: [content from ReviewerFile with placeholders filled]
+```
+
+**Inputs to provide:**
+- What was implemented (from implementer's report)
+- Plan or requirements reference
+- Base SHA and Head SHA for the git range
+- Brief description
+- `Language` and `ReviewerFile` from Stage B1b
+
+**Expected output when using an ECC reviewer:**
+- Severity breakdown: `CRITICAL`, `HIGH`, `MEDIUM`
+- Explicit verdict: `Approve`, `Warning`, or `Block`
+- File-level findings with remediation guidance
+
+**Verdict routing:**
+- `Block`: return task to implementer with specific findings; do not advance to Gate B until a subsequent review produces `Approve` or `Warning`
+- `Warning`: proceed to Gate B with MEDIUM findings visible in the task summary
+- `Approve`: proceed directly to Gate B
+
+**Diagnostic commands:**
+Language-specific reviewers may run diagnostic commands listed in their prompt files (for example `tsc --noEmit`, `eslint`, `mypy`, `go vet`, `cargo clippy`). If a command is unavailable in the environment, record the skip and continue the review rather than failing the entire review pass.
+
+**If issues found:**
+1. Send issues back to the implementer subagent for fixes
+2. Re-dispatch code quality reviewer after fixes
+3. Repeat until approved
+
+## Flow
+
+```dot
+digraph review_routing {
+    rankdir=TB;
+
+    "Task implementation complete" [shape=box];
+    "Dispatch spec reviewer\n(Phase 1)" [shape=box];
+    "Spec compliant?" [shape=diamond];
+    "Implementer fixes spec issues" [shape=box];
+    "Dispatch code quality reviewer\n(Phase 2)" [shape=box];
+    "Quality approved?" [shape=diamond];
+    "Implementer fixes quality issues" [shape=box];
+    "Task review complete" [shape=doublecircle];
+
+    "Task implementation complete" -> "Dispatch spec reviewer\n(Phase 1)";
+    "Dispatch spec reviewer\n(Phase 1)" -> "Spec compliant?";
+    "Spec compliant?" -> "Implementer fixes spec issues" [label="no"];
+    "Implementer fixes spec issues" -> "Dispatch spec reviewer\n(Phase 1)" [label="re-review"];
+    "Spec compliant?" -> "Dispatch code quality reviewer\n(Phase 2)" [label="yes"];
+    "Dispatch code quality reviewer\n(Phase 2)" -> "Quality approved?";
+    "Quality approved?" -> "Implementer fixes quality issues" [label="no"];
+    "Implementer fixes quality issues" -> "Dispatch code quality reviewer\n(Phase 2)" [label="re-review"];
+    "Quality approved?" -> "Task review complete" [label="yes"];
+}
+```
+
+## Red Flags
+
+**Never:**
+- Run code quality review before spec compliance passes
+- Run both reviews in parallel
+- Skip the re-review loop after fixes
+- Accept "close enough" on spec compliance
+- Let the implementer self-review replace either formal review
+
+**Always:**
+- Spec compliance first, code quality second
+- Loop until each phase passes
+- Provide full task context to each reviewer
+- Wait for user confirmation after both phases pass

package/prompts/build/phase-b-worktree.md

@@ -0,0 +1,215 @@
+<!-- SOURCE: skills/using-git-worktrees/SKILL.md -->
+
+# Using Git Worktrees
+
+## Overview
+
+Git worktrees create isolated workspaces sharing the same repository, allowing work on multiple branches simultaneously without switching.
+
+**Core principle:** Systematic directory selection + safety verification = reliable isolation.
+
+**Announce at start:** "I'm using the git-worktrees skill to set up an isolated workspace."
+
+## Directory Selection Process
+
+Follow this priority order:
+
+### 1. Check Existing Directories
+
+```bash
+# Check in priority order
+ls -d .worktrees 2>/dev/null     # Preferred (hidden)
+ls -d worktrees 2>/dev/null      # Alternative
+```
+
+**If found:** Use that directory. If both exist, `.worktrees` wins.
+
+### 2. Check CLAUDE.md
+
+```bash
+grep -i "worktree.*director" CLAUDE.md 2>/dev/null
+```
+
+**If preference specified:** Use it without asking.
+
+### 3. Ask User
+
+If no directory exists and no CLAUDE.md preference:
+
+```
+No worktree directory found. Where should I create worktrees?
+
+1. .worktrees/ (project-local, hidden)
+2. ~/.config/specflow/worktrees/<project-name>/ (global location)
+
+Which would you prefer?
+```
+
+## Safety Verification
+
+### For Project-Local Directories (.worktrees or worktrees)
+
+**MUST verify directory is ignored before creating worktree:**
+
+```bash
+# Check if directory is ignored (respects local, global, and system gitignore)
+git check-ignore -q .worktrees 2>/dev/null || git check-ignore -q worktrees 2>/dev/null
+```
+
+**If NOT ignored:**
+
+Fix broken things immediately:
+1. Add appropriate line to .gitignore
+2. Commit the change
+3. Proceed with worktree creation
+
+**Why critical:** Prevents accidentally committing worktree contents to repository.
+
+### For Global Directory (~/.config/specflow/worktrees)
+
+No .gitignore verification needed - outside project entirely.
+
+## Creation Steps
+
+### 1. Detect Project Name
+
+```bash
+project=$(basename "$(git rev-parse --show-toplevel)")
+```
+
+### 2. Create Worktree
+
+```bash
+# Determine full path
+case $LOCATION in
+  .worktrees|worktrees)
+    path="$LOCATION/$BRANCH_NAME"
+    ;;
+  ~/.config/specflow/worktrees/*)
+    path="~/.config/specflow/worktrees/$project/$BRANCH_NAME"
+    ;;
+esac
+
+# Create worktree with new branch
+git worktree add "$path" -b "$BRANCH_NAME"
+cd "$path"
+```
+
+### 3. Run Project Setup
+
+Auto-detect and run appropriate setup:
+
+```bash
+# Node.js
+if [ -f package.json ]; then npm install; fi
+
+# Rust
+if [ -f Cargo.toml ]; then cargo build; fi
+
+# Python
+if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+if [ -f pyproject.toml ]; then poetry install; fi
+
+# Go
+if [ -f go.mod ]; then go mod download; fi
+```
+
+### 4. Verify Clean Baseline
+
+Run tests to ensure worktree starts clean:
+
+```bash
+# Examples - use project-appropriate command
+npm test
+cargo test
+pytest
+go test ./...
+```
+
+**If tests fail:** Report failures, ask whether to proceed or investigate.
+
+**If tests pass:** Report ready.
+
+### 5. Report Location
+
+```
+Worktree ready at <full-path>
+Tests passing (<N> tests, 0 failures)
+Ready to implement <feature-name>
+```
+
+## Quick Reference
+
+| Situation | Action |
+|-----------|--------|
+| `.worktrees/` exists | Use it (verify ignored) |
+| `worktrees/` exists | Use it (verify ignored) |
+| Both exist | Use `.worktrees/` |
+| Neither exists | Check CLAUDE.md -> Ask user |
+| Directory not ignored | Add to .gitignore + commit |
+| Tests fail during baseline | Report failures + ask |
+| No package.json/Cargo.toml | Skip dependency install |
+
+## Common Mistakes
+
+### Skipping ignore verification
+
+- **Problem:** Worktree contents get tracked, pollute git status
+- **Fix:** Always use `git check-ignore` before creating project-local worktree
+
+### Assuming directory location
+
+- **Problem:** Creates inconsistency, violates project conventions
+- **Fix:** Follow priority: existing > CLAUDE.md > ask
+
+### Proceeding with failing tests
+
+- **Problem:** Can't distinguish new bugs from pre-existing issues
+- **Fix:** Report failures, get explicit permission to proceed
+
+### Hardcoding setup commands
+
+- **Problem:** Breaks on projects using different tools
+- **Fix:** Auto-detect from project files (package.json, etc.)
+
+## Example Workflow
+
+```
+You: I'm using the git-worktrees skill to set up an isolated workspace.
+
+[Check .worktrees/ - exists]
+[Verify ignored - git check-ignore confirms .worktrees/ is ignored]
+[Create worktree: git worktree add .worktrees/auth -b feature/auth]
+[Run npm install]
+[Run npm test - 47 passing]
+
+Worktree ready at /Users/dev/myproject/.worktrees/auth
+Tests passing (47 tests, 0 failures)
+Ready to implement auth feature
+```
+
+## Red Flags
+
+**Never:**
+- Create worktree without verifying it's ignored (project-local)
+- Skip baseline test verification
+- Proceed with failing tests without asking
+- Assume directory location when ambiguous
+- Skip CLAUDE.md check
+
+**Always:**
+- Follow directory priority: existing > CLAUDE.md > ask
+- Verify directory is ignored for project-local
+- Auto-detect and run project setup
+- Verify clean test baseline
+
+## Integration
+
+**Called by:**
+- **specflow:refine** (Phase 4) - REQUIRED when design is approved and implementation follows
+- **specflow:build Phase B** - REQUIRED before executing any tasks
+- **specflow:build Phase B (inline mode)** - REQUIRED before executing any tasks
+- Any skill needing isolated workspace
+
+**Pairs with:**
+- **specflow:done** - REQUIRED for cleanup after work complete

package/prompts/build/plan-document-reviewer.md

@@ -0,0 +1,51 @@
+<!-- SOURCE: skills/writing-plans/plan-document-reviewer-prompt.md -->
+
+# Plan Document Reviewer Prompt Template
+
+Use this template when dispatching a plan document reviewer subagent.
+
+**Purpose:** Verify the plan is complete, matches the spec, and has proper task decomposition.
+
+**Dispatch after:** The complete plan is written.
+
+```
+Task tool (general-purpose):
+  description: "Review plan document"
+  prompt: |
+    You are a plan document reviewer. Verify this plan is complete and ready for implementation.
+
+    **Plan to review:** [PLAN_FILE_PATH]
+    **Spec for reference:** [SPEC_FILE_PATH]
+
+    ## What to Check
+
+    | Category | What to Look For |
+    |----------|------------------|
+    | Completeness | TODOs, placeholders, incomplete tasks, missing steps |
+    | Spec Alignment | Plan covers spec requirements, no major scope creep |
+    | Task Decomposition | Tasks have clear boundaries, steps are actionable |
+    | Buildability | Could an engineer follow this plan without getting stuck? |
+
+    ## Calibration
+
+    **Only flag issues that would cause real problems during implementation.**
+    An implementer building the wrong thing or getting stuck is an issue.
+    Minor wording, stylistic preferences, and "nice to have" suggestions are not.
+
+    Approve unless there are serious gaps -- missing requirements from the spec,
+    contradictory steps, placeholder content, or tasks so vague they can't be acted on.
+
+    ## Output Format
+
+    ## Plan Review
+
+    **Status:** Approved | Issues Found
+
+    **Issues (if any):**
+    - [Task X, Step Y]: [specific issue] - [why it matters for implementation]
+
+    **Recommendations (advisory, do not block approval):**
+    - [suggestions for improvement]
+```
+
+**Reviewer returns:** Status, Issues (if any), Recommendations