prizmkit 1.1.79 → 1.1.80

package/bundled/skills/feature-workflow/references/brainstorm-guide.md

@@ -0,0 +1,137 @@
+# Brainstorm Guide — Detailed Procedures
+
+Procedural details for Phase 1 brainstorming in feature-workflow.
+
+## Step 1.3: Parallel Deep Reading
+
+**Goal**: Build comprehensive understanding of the project context before discussing detailed requirements. Spawn multiple agents in parallel to read all relevant materials simultaneously.
+
+**Parallel reading tasks** (launch concurrently):
+
+| Agent | What to read | Purpose |
+|-------|-------------|---------|
+| Agent A | User-provided code paths — read existing source files | Understand current architecture, patterns, conventions |
+| Agent B | User-provided documents — design docs, specs, PRDs | Understand intended requirements and constraints |
+| Agent C | `.prizmkit/prizm-docs/` — root.prizm, L1/L2 docs, TRAPS, RULES | Understand existing architecture knowledge and known pitfalls |
+| Agent D | Database/schema files + `.prizmkit/config.json` | Understand data model and tech stack preferences |
+
+**Also gather** (can be included in any agent's task):
+- Directory structure of the project
+- Existing test patterns and conventions
+- Dependency relationships between existing modules
+
+**After all agents complete**: Synthesize findings into a coherent understanding before proceeding to discussion.
+
+## Step 1.4: Discuss Requirements
+
+**Now** — with deep knowledge of the actual codebase and documents — discuss the requirements with the user. This discussion is grounded in real context, not abstract questions.
+
+Present what you learned from the parallel reading:
+- Current project structure and patterns (with specific references)
+- Existing data model and schema conventions
+- Known TRAPS and pitfalls from `.prizmkit/prizm-docs/`
+- Integration points with existing modules
+
+Then ask targeted questions based on what you read. **Adapt question depth to the feature complexity** — a simple CRUD feature needs fewer questions than a real-time collaboration system.
+
+### Functional Requirements
+- What are the core user actions/workflows?
+- What inputs does the system accept? What outputs does it produce?
+- What are the key business rules and validation logic?
+- Are there different user roles with different permissions?
+
+### Data Model & Database (if applicable)
+- What entities/data need to be stored?
+- What are the relationships between entities?
+- Are there existing database tables this feature must integrate with?
+- What fields are required vs optional? What data types?
+- Any unique constraints, indexes, or special query patterns needed?
+- **RULE**: If the project has existing database tables, ALL new table designs must reference and conform to the existing schema style (naming conventions, ID strategy, timestamp patterns, constraint patterns). Ask the user to confirm the data model before proceeding.
+
+### User Experience
+- What does the user see and interact with?
+- What is the expected flow/sequence of actions?
+- How should errors be displayed to the user?
+- Are there any specific UI/UX requirements?
+
+### Integration & Architecture
+- "Based on the existing code, this feature would integrate with [modules]. Does that match your expectations?"
+- Any external APIs or services involved?
+- What authentication/authorization model applies?
+- Any real-time requirements (WebSocket, SSE, polling)?
+
+### Edge Cases & Error Handling
+- What happens when things go wrong? (network failure, invalid input, concurrent access)
+- What are the boundary conditions? (empty states, max limits, permissions denied)
+- Any rate limiting, quotas, or resource constraints?
+
+### Non-Functional Requirements
+- Performance expectations? (response time, throughput)
+- Scalability considerations?
+- Security requirements? (encryption, audit logs, compliance)
+
+## Comparison with Alternative Workflows
+
+| Dimension | feature-workflow | bug-fix-workflow | refactor-workflow |
+|-----------|-----------------|------------------|--------------------|
+| **Purpose** | New features (batch) | Single bug fix (interactive) | Code restructuring (batch) |
+| **Brainstorming** | Yes — collect materials, parallel read, discuss | No (bug report is input) | Yes — clarify type, collect materials, parallel read, discuss |
+| **Planning Skill** | `feature-planner` | None (triage built-in) | `refactor-planner` |
+| **Branch** | Pipeline manages per-feature | `fix/<BUG_ID>-*` | Pipeline manages per-refactor |
+| **Execution** | Foreground or background daemon | In-session, interactive | Foreground or background daemon |
+| **Input** | Rough idea or requirements | Bug report / stack trace | Rough refactoring idea or target |
+| **Output** | Multiple `feat()` commits | Single `fix()` commit | Multiple `refactor()` commits |
+| **Behavior Change** | Expected (new functionality) | Fix behavior | Forbidden (structure only) |
+| **Batch alternative** | (this is the batch flow) | `bug-planner` + `bugfix-pipeline-launcher` | (this is the batch flow) |
+
+## Completion Signs
+
+**Signs that brainstorming is complete:**
+- All functional requirements have concrete acceptance criteria
+- Data model entities and relationships are defined
+- Edge cases and error handling are addressed
+- Integration points are identified
+- The user has confirmed the summary is accurate
+
+**Signs that more questions are needed:**
+- User's answers contain vague terms ("handle it appropriately", "make it user-friendly", "standard behavior")
+- Core business rules are undefined ("depends on the situation")
+- Data relationships are unclear ("somehow connected")
+- User says "I'm not sure" — help them think through it with concrete options
+
+## Requirements Summary Template
+
+Once brainstorming is complete, produce a structured requirements summary using the following format. Present the summary to the user and get explicit confirmation before proceeding.
+
+```markdown
+## Requirements Summary
+
+### Project/Feature: [Name]
+
+### Core Functionality
+- [Bullet list of what the system does]
+
+### User Roles
+- [Role]: [What they can do]
+
+### Data Model Overview
+- [Entity]: [Key fields, relationships]
+
+### Key Business Rules
+- [Rule 1]
+- [Rule 2]
+
+### Integration Points
+- [External system/API/module]
+
+### Edge Cases & Error Handling
+- [Case]: [Expected behavior]
+
+### Non-Functional Requirements
+- [Requirement]
+
+### Reference Materials Reviewed
+- [List of code paths, documents, .prizmkit/prizm-docs/ files that were read]
+
+### Confirmed by user: ✓
+```

package/bundled/skills/prizm-kit/SKILL.md

@@ -5,6 +5,17 @@ description: "Full-lifecycle dev toolkit index. Routes to the right PrizmKit ski
 
 # PrizmKit — Full-Lifecycle Development Toolkit
 
+### When to Use
+- User asks "which command?", "help", "how do I start a feature", "get started", "what tools"
+- User wants to understand the PrizmKit development lifecycle
+- User invokes "/prizmkit" or asks about dev workflow
+- User is new to the project and needs orientation
+
+### When NOT to Use
+- User already knows which specific skill to use — invoke it directly
+- Mid-implementation — use the specific skill needed (/prizmkit-implement, /prizmkit-code-review, etc.)
+- User wants to execute immediately without orientation — go directly to /prizmkit-plan or /prizmkit-implement
+
 ## Task Execution Model
 
 PrizmKit uses **headless mode** — each task runs as an independent AI CLI session with NO context carryover between tasks. Every session starts by reading docs and ends by maintaining docs.

package/bundled/skills/prizmkit-code-review/SKILL.md

@@ -32,108 +32,98 @@ The loop repeats until the Reviewer finds no issues or the max round limit is re
 
 1. **Read spec.md** from the artifact directory — extract goals and acceptance criteria.
 2. **Read plan.md** from the artifact directory — extract architecture decisions and completed tasks.
-3. **Read dev rules** (if configured): Read `.prizmkit/prizm-docs/root.prizm` and check for a `RULES:` line. If present, read all referenced `.prizmkit/rules/<layer>-rules.md` files. If a referenced file does not exist, skip it silently and continue. These define per-layer conventions that the code should follow.
+3. **Read dev rules** (if configured): If `.prizmkit/prizm-docs/root.prizm` exists, read it and check for a `RULES:` line. If present, read all referenced `.prizmkit/rules/<layer>-rules.md` files. If `root.prizm` or a referenced rules file does not exist, continue with "No custom dev rules configured — use general best practices."
 4. **Capture workspace diff**: run `git diff` (unstaged) + `git diff --cached` (staged) + `git status` to understand the full scope of changes. For new files in git status, note their paths for the Reviewer to read.
-   - If no changes are detected, output PASS and stop.
+   - If no changes are detected, skip Phase 1 and proceed to Phase 2 with verdict PASS, rounds 0, and an empty findings list. Always write `review-report.md`; downstream pipeline steps use it as the review gate.
 
 ## Phase 1: Review-Fix Loop
 
-```
-┌─── Loop (max 3 rounds) ──────────────────────────────┐
-│                                                        │
-│  Step 1: Spawn Reviewer Agent (read-only)              │
-│    → Input: git diff + spec goals + plan decisions + dev rules│
-│    → Output: structured findings or PASS               │
-│                                                        │
-│  Step 2: Check result                                  │
-│    → If PASS (no findings): exit loop                  │
-│                                                        │
-│  Step 3: Main Agent filters findings                   │
-│    → For each finding: accept (reasonable) or reject   │
-│    → If all rejected: exit loop                        │
-│                                                        │
-│  Step 4: Spawn Dev Agent (read-write)                  │
-│    → Input: accepted findings + spec/plan context      │
-│    → Output: fix report                                │
-│                                                        │
-│  Step 5: Back to Step 1                                │
-│                                                        │
-│  Hard limit: exit after 3 rounds regardless            │
-│  → On max-round exhaustion: output a summary of all    │
-│    unresolved findings to the conversation, then write  │
-│    review-report.md with NEEDS_FIXES verdict.           │
-└────────────────────────────────────────────────────────┘
+### Gate Mode Detection
+
+The loop exit conditions are enforced by a gatekeeper. Check Python availability first:
+
+```bash
+python3 --version 2>/dev/null && echo "SCRIPT_MODE" || echo "TEXT_MODE"
 ```
 
-### Step 1: Spawn Reviewer Agent
+- **Script mode** (Python available): Use `${SKILL_DIR}/scripts/check_loop.py` to enforce exit conditions with round tracking, max-rounds enforcement, and divergence detection. The script prevents accidentally exceeding the 3-round limit.
+- **Text mode** (no Python): Follow §Text Fallback Constraints — identical behavior enforced manually.
+
+### Step 0: Initialize Loop State
+
+The script is stateless — no `--reset` or runtime files. Initialize these values before starting:
 
-Include the dev rules read in Phase 0 step 3 in the `## Dev Rules` section of the prompt below. Spawn a **read-only** agent (subagent_type: `Explore`) with the following prompt:
+**Script mode** — `findings_history = []`, `max_rounds = 3`, `round = 1`.
+**Text mode** — track manually: `round = 1`, `findings_history = []`.
 
+### Loop Flow
+
+```
+1. Spawn Reviewer Agent (read-only) → findings or PASS
+2. Parse result:
+   - PASS → Call Loop Exit Gate → Phase 2
+   - NEEDS_FIXES → count findings → Step 3 (do not call gate yet)
+3. Main Agent filters findings → Call Loop Exit Gate → if endLoop: Phase 2
+4. Spawn Dev Agent (read-write) → apply fixes
+5. Increment round and return to Step 1
 ```
-You are a code reviewer. Review workspace changes against the spec goals, plan decisions, and per-layer dev rules.
 
-## Spec Goals
-{goals and acceptance criteria from spec.md}
+### Loop Exit Gate
+
+Call the gate only in these cases:
 
-## Plan Decisions
-{architecture decisions and task list from plan.md}
+1. Reviewer returned `PASS`.
+2. Main Agent has finished filtering `NEEDS_FIXES` findings.
 
-## Dev Rules (per-layer conventions)
-{rules from .prizmkit/rules/<layer>-rules.md, or "No custom dev rules configured — use general best practices."}
+Do not call the gate for `NEEDS_FIXES` before filtering, because `accepted_count` is not known yet. Only exit the loop when `endLoop` is `true` — the gate is the sole authority on exit decisions.
 
-## Review Round
-Round {N}. {round_context}
+**Script mode invocation:**
+```bash
+echo '{"reviewer_result":"NEEDS_FIXES","accepted_count":2,"findings_count":3,"round":1,"findings_history":[],"max_rounds":3,"filtering_done":true}' | python3 ${SKILL_DIR}/scripts/check_loop.py
+```
 
-## What to Review
-Run these commands to see the current workspace changes:
-- `git diff` (unstaged changes)
-- `git diff --cached` (staged changes)
-- `git status` (new/deleted files)
+| Input field | Type | Description |
+|-------------|------|-------------|
+| `reviewer_result` | `"PASS"` or `"NEEDS_FIXES"` | Reviewer's verdict |
+| `accepted_count` | int | Findings accepted by Main Agent. Use `0` for Reviewer PASS or when all findings were rejected after filtering. |
+| `findings_count` | int | Total findings returned by Reviewer this round |
+| `round` | int | Current round number (1-based, model-supplied — the script does not auto-increment) |
+| `findings_history` | `[int, ...]` | Findings count per round, used for divergence detection. Initialize as `[]`. Pass back the value from the previous gate call's output. |
+| `max_rounds` | int | Maximum review rounds before forced exit. Default `3`. |
+| `filtering_done` | bool | `true` only after Main Agent has filtered `NEEDS_FIXES` findings. For Reviewer PASS, this may be omitted. |
 
-For new files shown in git status, read their full content.
-For modified files, read enough surrounding context to understand the change.
+Output: `{"endLoop": bool, "reason": str, "verdict": "PASS"|"NEEDS_FIXES"|null, "round": int, "maxRounds": int, "divergenceWarning": bool, "findings_history": [int, ...]}`
 
-## Review Dimensions
-Evaluate the changes across these dimensions (focus on what's relevant):
+The script enforces three exit conditions in order: (1) Reviewer PASS → exit with verdict PASS, (2) filtered `NEEDS_FIXES` with zero accepted findings → exit with verdict PASS, (3) max rounds reached after filtering → exit with verdict NEEDS_FIXES. It records `findings_count` once per round by round index, so repeated gate calls cannot duplicate history entries. If `divergenceWarning` is true, warn the user the loop may not be converging.
 
-1. **Goal alignment**: Do the changes accomplish all goals from spec.md? Anything missing or off-target?
-2. **Defects**: Logic bugs, missing error handling, boundary condition issues, incorrect behavior.
-3. **Completeness**: Files that should have been changed but weren't? Missing tests, types, imports, exports?
-4. **Consistency**: Do changes follow the project's existing patterns, naming conventions, and code style?
-5. **Security**: Hardcoded secrets, injection vulnerabilities, unsafe operations.
-6. **Rules compliance**: (Skip this dimension if no dev rules were provided.) Do changes follow the per-layer dev rules? Flag violations of framework conventions, naming patterns, state management, or other rules defined for that layer.
+**Text mode** — enforce §Text Fallback Constraints manually with identical logic.
 
-## Output Format
-Respond with EXACTLY this format:
+### Text Fallback Constraints
 
-### Result: PASS | NEEDS_FIXES
+When Python is unavailable, apply these rules exactly — they match the script's logic:
 
-### Findings
-(If PASS, write "No issues found.")
+1. **PASS exit**: Reviewer returns `PASS` → exit loop, verdict PASS.
+2. **Pre-filter NEEDS_FIXES**: Count findings and continue to filtering. Do not apply all-rejected or max-round exits before filtering.
+3. **All-rejected exit**: After filtering, if all findings were rejected → exit loop, verdict PASS.
+4. **Max rounds**: After filtering, if `round >= 3` and accepted findings remain → exit loop, verdict NEEDS_FIXES. Write `review-report.md` with unresolved findings.
+5. **Divergence**: If findings count strictly increases for 3 consecutive recorded rounds, warn user the loop may not converge.
+6. **Counter**: Increment `round` after each complete cycle (Steps 1-4). Track `findings_history` by round index to detect divergence — record `findings_count` once per round.
 
-#### Finding N
-- **Severity**: high | medium | low
-- **Dimension**: goal-alignment | defect | completeness | consistency | security | rules-compliance
-- **Location**: filepath:line (or "project-level")
-- **Problem**: What is wrong and why it matters
-- **Suggestion**: Recommended fix approach
-- **Verification**: How to confirm the fix is correct
+### Step 1: Spawn Reviewer Agent
 
-### Summary
-One to two sentences about the overall state of the changes.
-```
+Include the dev rules read in Phase 0 step 3 in the `## Dev Rules` section of the prompt. Spawn a platform-supported **read-only** reviewer agent; use `subagent_type: Explore` only on platforms that support it. If no read-only agent is available, perform the review in the Main Agent without editing files. Read `${SKILL_DIR}/references/reviewer-agent-prompt.md` for the full prompt template — fill `{goals}`, `{plan decisions}`, `{dev rules}`, `{round N}`, and `{round_context}` before spawning.
 
-**Round context** varies by round:
+Round context varies by round:
 - Round 1: "This is the first review. Examine all changes comprehensively."
 - Round 2+: "Previous round found issues that were fixed. Focus on: (1) whether previous fixes are correct, (2) whether fixes introduced new problems, (3) any remaining issues. Do not re-report issues that have already been fixed."
 
-### Step 2: Check Result
+### Step 2: Check Result + Gate
 
 Parse the Reviewer Agent's output:
-- If `Result: PASS` → exit loop, proceed to Phase 2.
-- If `Result: NEEDS_FIXES` → extract findings and continue to Step 3.
+- If `Result: PASS` → call the **Loop Exit Gate** with `{"reviewer_result": "PASS", "accepted_count": 0, "findings_count": 0, "round": <current_round>, "findings_history": <current_history>, "max_rounds": 3}`. If `endLoop=true`, proceed to Phase 2.
+- If `Result: NEEDS_FIXES` → count findings, do not call the gate yet, then continue to Step 3.
 
-### Step 3: Main Agent Filters Findings
+### Step 3: Main Agent Filters Findings + Gate
 
 Review each finding and decide whether it's reasonable. This prevents unnecessary or harmful changes.
 
@@ -146,76 +136,17 @@ Review each finding and decide whether it's reasonable. This prevents unnecessar
 - **Accepted**: The finding is reasonable — include it in the Dev Agent's task.
 - **Rejected** (with reason): Brief explanation (e.g., "Out of scope", "Style preference, not a defect").
 
-If all findings are rejected → exit loop, proceed to Phase 2.
+After filtering: call the **Loop Exit Gate** with `{"reviewer_result": "NEEDS_FIXES", "accepted_count": <N>, "findings_count": <total findings this round>, "round": <current_round>, "findings_history": <current_history>, "max_rounds": 3, "filtering_done": true}`. If `endLoop=true`, proceed to Phase 2.
 
 ### Step 4: Spawn Dev Agent
 
-Spawn a **general-purpose** agent (read-write) with the following prompt:
-
-```
-You are a developer fixing code review findings. Apply each fix carefully without breaking existing functionality.
-
-## Spec Context
-{goals from spec.md for reference}
-
-## Findings to Fix
-{accepted findings list — each with Severity, Location, Problem, Suggestion, Verification}
-
-## Instructions
-1. Read each finding carefully.
-2. For each finding:
-   a. Read the relevant code and understand the context.
-   b. Implement the fix based on the suggestion.
-   c. If a suggestion is not feasible (would break other functionality, technically impossible), explain why.
-3. After all fixes, report what you did.
-
-## Output Format
-For each finding, report:
-- **Finding N**: [fixed | unable-to-fix]
-- **What was done**: Brief description
-- **Files modified**: List of changed files
-(If unable-to-fix, explain why)
-```
+Spawn a platform-supported **read-write** developer agent. If no write-capable agent is available, the Main Agent applies accepted fixes directly. Read `${SKILL_DIR}/references/dev-agent-prompt.md` for the full prompt template — fill `{spec context}` and `{accepted findings}` before spawning.
 
 After the Dev Agent returns, record results and return to Step 1 for the next round.
 
 ## Phase 2: Output
 
-Write `review-report.md` to the artifact directory:
-
-```markdown
-# Review Report
-
-## Verdict: PASS
-## Rounds: 2
-## Total findings: 3 → Fixed: 2, Rejected: 1
-
-## Round 1
-Findings: 3 | Accepted: 2, Rejected: 1
-
-### Finding 1: Missing null check in parseConfig
-- Severity: high
-- Dimension: defect
-- Location: src/config.ts:42
-- Problem: parseConfig crashes when input is undefined
-- Status: fixed (round 1)
-
-### Finding 2: Export missing from index.ts
-- Severity: medium
-- Dimension: completeness
-- Location: src/index.ts
-- Problem: New parseConfig function not exported
-- Status: fixed (round 1)
-
-### Finding 3: Consider renaming variable
-- Severity: low
-- Dimension: consistency
-- Location: src/config.ts:15
-- Problem: Variable `d` should be more descriptive
-- Status: rejected — Style preference; existing code uses short names in this module
-
-## Round 2: PASS — no new findings
-```
+Always write `review-report.md` to the artifact directory, including no-change PASS results. Read `${SKILL_DIR}/references/review-report-template.md` for the full output format.
 
 - `PASS`: Reviewer returned no findings (or all remaining findings were rejected as unreasonable)
 - `NEEDS_FIXES`: 3 rounds completed but unresolved findings remain

package/bundled/skills/prizmkit-code-review/references/dev-agent-prompt.md

@@ -0,0 +1,30 @@
+# Dev Agent Prompt Template
+
+Used in Phase 1 Step 4 of `/prizmkit-code-review`. The orchestrator fills `{spec context}` and `{accepted findings}` before spawning the Dev Agent.
+
+```
+You are a developer fixing code review findings. Apply each fix carefully without breaking existing functionality.
+
+## Spec Context
+{goals from spec.md for reference}
+
+## Findings to Fix
+{accepted findings list — each with Severity, Location, Problem, Suggestion, Verification}
+
+## Instructions
+1. Read each finding carefully.
+2. For each finding:
+   a. Read the relevant code and understand the context.
+   b. Implement the fix based on the suggestion.
+   c. If a suggestion is not feasible (would break other functionality, technically impossible), explain why.
+3. After all fixes, report what you did.
+
+## Output Format
+For each finding, report:
+- **Finding N**: [fixed | unable-to-fix]
+- **What was done**: Brief description
+- **Files modified**: List of changed files
+(If unable-to-fix, explain why)
+```
+
+After the Dev Agent returns, record results and return to Step 1 for the next round.

package/bundled/skills/prizmkit-code-review/references/review-report-template.md

@@ -0,0 +1,31 @@
+# Review Report Output Template
+
+Used in Phase 2 of `/prizmkit-code-review`. Always write `review-report.md` to the artifact directory using this format.
+
+```markdown
+# Review Report
+
+## Verdict: <PASS|NEEDS_FIXES>
+## Rounds: <number of review rounds completed; use 0 for no-change PASS>
+## Total findings: <total> → Fixed: <fixed>, Rejected: <rejected>, Unresolved: <unresolved>
+
+## Round <N>
+Findings: <count> | Accepted: <count>, Rejected: <count>
+
+### Finding <N>: <short title>
+- Severity: <high|medium|low>
+- Dimension: <goal-alignment|defect|completeness|consistency|security|rules-compliance>
+- Location: <filepath:line or project-level>
+- Problem: <what was wrong and why it mattered>
+- Status: <fixed (round N)|rejected — reason|unresolved — reason>
+
+## Final Summary
+<One to three sentences summarizing the review outcome, including no-change PASS when applicable.>
+```
+
+For `PASS` with no findings, write `Total findings: 0 → Fixed: 0, Rejected: 0, Unresolved: 0` and `## Round 0: PASS — no workspace changes to review` or `## Round N: PASS — no issues found`.
+
+## Verdict Rules
+
+- `PASS`: Reviewer returned no findings, no workspace changes existed, or all remaining findings were rejected as unreasonable.
+- `NEEDS_FIXES`: Max rounds completed but accepted findings remain unresolved.

package/bundled/skills/prizmkit-code-review/references/reviewer-agent-prompt.md

@@ -0,0 +1,62 @@
+# Reviewer Agent Prompt Template
+
+Used in Phase 1 Step 1 of `/prizmkit-code-review`. The orchestrator fills `{goals}`, `{plan decisions}`, `{dev rules}`, `{round N}`, and `{round_context}` before spawning the Reviewer Agent.
+
+```
+You are a code reviewer. Review workspace changes against the spec goals, plan decisions, and per-layer dev rules.
+
+## Spec Goals
+{goals and acceptance criteria from spec.md}
+
+## Plan Decisions
+{architecture decisions and task list from plan.md}
+
+## Dev Rules (per-layer conventions)
+{rules from .prizmkit/rules/<layer>-rules.md, or "No custom dev rules configured — use general best practices."}
+
+## Review Round
+Round {N}. {round_context}
+
+## What to Review
+Run these commands to see the current workspace changes:
+- `git diff` (unstaged changes)
+- `git diff --cached` (staged changes)
+- `git status` (new/deleted files)
+
+For new files shown in git status, read their full content.
+For modified files, read enough surrounding context to understand the change.
+
+## Review Dimensions
+Evaluate the changes across these dimensions (focus on what's relevant):
+
+1. **Goal alignment**: Do the changes accomplish all goals from spec.md? Anything missing or off-target?
+2. **Defects**: Logic bugs, missing error handling, boundary condition issues, incorrect behavior.
+3. **Completeness**: Files that should have been changed but weren't? Missing tests, types, imports, exports?
+4. **Consistency**: Do changes follow the project's existing patterns, naming conventions, and code style?
+5. **Security**: Hardcoded secrets, injection vulnerabilities, unsafe operations.
+6. **Rules compliance**: (Skip this dimension if no dev rules were provided.) Do changes follow the per-layer dev rules? Flag violations of framework conventions, naming patterns, state management, or other rules defined for that layer.
+
+## Output Format
+Respond with EXACTLY this format:
+
+### Result: PASS | NEEDS_FIXES
+
+### Findings
+(If PASS, write "No issues found.")
+
+#### Finding N
+- **Severity**: high | medium | low
+- **Dimension**: goal-alignment | defect | completeness | consistency | security | rules-compliance
+- **Location**: filepath:line (or "project-level")
+- **Problem**: What is wrong and why it matters
+- **Suggestion**: Recommended fix approach
+- **Verification**: How to confirm the fix is correct
+
+### Summary
+One to two sentences about the overall state of the changes.
+```
+
+## Round Context
+
+- Round 1: "This is the first review. Examine all changes comprehensively."
+- Round 2+: "Previous round found issues that were fixed. Focus on: (1) whether previous fixes are correct, (2) whether fixes introduced new problems, (3) any remaining issues. Do not re-report issues that have already been fixed."