planflow-ai 1.4.1 → 1.4.4

package/.claude/commands/brainstorm.md

@@ -179,22 +179,15 @@ After the skill completes:
 +------------------------------------------+
 ```
 
----
-
-## Context Optimization
-
-### Recommended Loading Order
+## Context Loading
 
-1. **Always load first**: This command file (`commands/brainstorm.md`)
-2. **Expand on-demand**: Load skill file when entering conversational loop
+This command uses the **brain index** for context retrieval. Before executing, query the project brain for relevant documentation:
 
-### Reference Codes for Brainstorm
+**Queries**:
+- `planflow-ai state-query "brainstorm workflow" --scope resources`
+- `planflow-ai state-query "interactive questions" --scope resources`
 
-| Code | Description | When to Expand |
-|------|-------------|----------------|
-| SKL-BS-1 | Brainstorm skill restrictions and inputs | Understanding allowed actions |
-| SKL-BS-2 | Conversational loop and tracking | During the brainstorm |
-| SKL-BS-3 | End detection, summary, and output | When wrapping up |
+The brain returns ranked chunks from indexed markdown files. Use the top results to inform execution.
 
 ---
 
@@ -202,7 +195,6 @@ After the skill completes:
 
 | Resource | Purpose |
 |----------|---------|
-| `resources/skills/_index.md` | Index of skills with reference codes |
 | `brainstorm-skill.md` | Skill that runs the brainstorm |
 | `brainstorm-templates.md` | Output file template |
 | `/discovery-plan` command | Next step after brainstorm |

package/.claude/commands/create-contract.md

@@ -193,44 +193,15 @@ The user will read the `.md` file themselves and decide when to proceed.
 4. Present contract summary
 5. User reviews and proceeds to `/discovery-plan`
 
----
-
-## Context Optimization
-
-This command uses hierarchical context loading to reduce context consumption. Instead of loading full files, load indexes first and expand specific sections on-demand.
-
-### Recommended Loading Order
-
-1. **Always load first**: This command file (`commands/create-contract.md`)
-2. **Load indexes**: Load `_index.md` files for relevant folders
-3. **Expand on-demand**: Use reference codes to load specific sections when needed
-
-### Index Files for Contract Creation
-
-| Index | When to Load |
-|-------|--------------|
-| `resources/patterns/_index.md` | To find contract patterns |
-| `resources/skills/_index.md` | To understand skill workflow |
-| `resources/tools/_index.md` | When using interactive questions |
-
-### Reference Codes for Contract Creation
-
-| Code | Description | When to Expand |
-|------|-------------|----------------|
-| PTN-CON-1 | Contract document structure | Creating new contract |
-| PTN-CON-2 | Endpoint documentation format | Documenting API endpoints |
-| SKL-CON-1 | Contract skill workflow | Understanding full process |
-| TLS-IQ-2 | How to switch to Plan mode | Before asking questions |
-| TLS-IQ-3 | How to ask questions | When gathering scope info |
+## Context Loading
 
-### Expansion Instructions
+This command uses the **brain index** for context retrieval. Before executing, query the project brain for relevant documentation:
 
-When executing this command:
+**Queries**:
+- `planflow-ai state-query "contract creation" --scope resources`
+- `planflow-ai state-query "contract patterns" --scope resources`
 
-1. **Start with indexes**: Read `resources/patterns/_index.md` and `resources/skills/_index.md`
-2. **Identify needed codes**: Based on current step, identify which codes are relevant
-3. **Expand as needed**: Use the Read tool with specific line ranges from the index
-4. **Don't expand everything**: Only load content required for the current step
+The brain returns ranked chunks from indexed markdown files. Use the top results to inform execution.
 
 ---
 
@@ -238,9 +209,6 @@ When executing this command:
 
 | Resource                       | Purpose                                |
 | ------------------------------ | -------------------------------------- |
-| `resources/skills/_index.md`      | Index of skills with reference codes   |
-| `resources/patterns/_index.md`    | Index of patterns with reference codes |
-| `resources/tools/_index.md`       | Index of tools with reference codes    |
 | `create-contract-skill.md`    | Skill that creates the contract        |
 | `contract-patterns.md`        | Rules and patterns for contracts       |
 | `interactive-questions-tool.md` | Interactive Questions UI workflow    |

package/.claude/commands/create-plan.md

@@ -221,44 +221,16 @@ The user will read the `.md` file themselves and decide when to proceed.
 5. Present plan summary
 6. User reviews and proceeds to `/execute-plan`
 
----
-
-## Context Optimization
-
-This command uses hierarchical context loading to reduce context consumption. Instead of loading full files, load indexes first and expand specific sections on-demand.
-
-### Recommended Loading Order
-
-1. **Always load first**: This command file (`commands/create-plan.md`)
-2. **Load indexes**: Load `_index.md` files for relevant folders
-3. **Expand on-demand**: Use reference codes to load specific sections when needed
-
-### Index Files for Plan Creation
-
-| Index | When to Load |
-|-------|--------------|
-| `resources/patterns/_index.md` | To find plan patterns and templates |
-| `resources/skills/_index.md` | To understand skill workflow |
-| `resources/core/_index.md` | For complexity scoring reference |
-
-### Reference Codes for Plan Creation
-
-| Code | Description | When to Expand |
-|------|-------------|----------------|
-| PTN-PLN-1 | Plan document structure | Creating new plan |
-| PTN-PLN-2 | Phase organization | Structuring phases |
-| PTN-PLNT-1 | Plan template | Creating output file |
-| SKL-PLN-1 | Create plan skill workflow | Understanding full process |
-| COR-CS-1 | Complexity scoring table | Assigning complexity scores |
+## Context Loading
 
-### Expansion Instructions
+This command uses the **brain index** for context retrieval. Before executing, query the project brain for relevant documentation:
 
-When executing this command:
+**Queries**:
+- `planflow-ai state-query "plan creation" --scope resources`
+- `planflow-ai state-query "complexity scoring" --scope resources`
+- `planflow-ai state-query "phase structure" --scope resources`
 
-1. **Start with indexes**: Read `resources/patterns/_index.md` and `resources/core/_index.md`
-2. **Identify needed codes**: Based on current step, identify which codes are relevant
-3. **Expand as needed**: Use the Read tool with specific line ranges from the index
-4. **Don't expand everything**: Only load content required for the current step
+The brain returns ranked chunks from indexed markdown files. Use the top results to inform execution.
 
 ---
 
@@ -266,9 +238,6 @@ When executing this command:
 
 | Resource                    | Purpose                           |
 | --------------------------- | --------------------------------- |
-| `resources/skills/_index.md`   | Index of skills with reference codes |
-| `resources/patterns/_index.md` | Index of patterns with reference codes |
-| `resources/core/_index.md`     | Index of core rules with reference codes |
 | `create-plan-skill.md`     | Skill that creates the plan       |
 | `plans-patterns.md`        | Rules and patterns for plans      |
 | `plans-templates.md`       | Plan templates                    |

package/.claude/commands/discovery-plan.md

@@ -248,55 +248,16 @@ The user will read the `.md` file themselves and decide when to proceed.
 6. User reviews and requests refinements (if any)
 7. User invokes `/create-plan` when ready
 
----
-
-## Context Optimization
-
-This command uses hierarchical context loading to reduce context consumption. Instead of loading full files, load indexes first and expand specific sections on-demand.
-
-### Recommended Loading Order
-
-1. **Always load first**: This command file (`commands/discovery-plan.md`)
-2. **Load indexes**: Load `_index.md` files for relevant folders
-3. **Expand on-demand**: Use reference codes to load specific sections when needed
-
-### Index Files for Discovery
-
-| Index | When to Load |
-|-------|--------------|
-| `resources/patterns/_index.md` | To find discovery templates and patterns |
-| `resources/skills/_index.md` | To understand skill workflow |
-| `resources/tools/_index.md` | When using interactive questions |
+## Context Loading
 
-### Reference Codes for Discovery
+This command uses the **brain index** for context retrieval. Before executing, query the project brain for relevant documentation:
 
-| Code | Description | When to Expand |
-|------|-------------|----------------|
-| PTN-DIS-1 | Discovery document structure | Creating new discovery doc |
-| PTN-DIS-2 | Requirements gathering example | Need example format |
-| PTN-DIST-1 | Discovery template | Creating output file |
-| SKL-DIS-1 | Discovery skill workflow | Understanding full process |
-| TLS-IQ-2 | How to switch to Plan mode | Before asking questions |
-| TLS-IQ-3 | How to ask questions | When gathering requirements |
-| COR-CG-1 | Compaction guide | Load when compacting mid-discovery |
+**Queries**:
+- `planflow-ai state-query "discovery workflow" --scope resources`
+- `planflow-ai state-query "requirements gathering" --scope resources`
+- `planflow-ai state-query "codebase analysis" --scope resources`
 
-### Expansion Instructions
-
-When executing this command:
-
-1. **Start with indexes**: Read `resources/patterns/_index.md` and `resources/skills/_index.md`
-2. **Identify needed codes**: Based on current step, identify which codes are relevant
-3. **Expand as needed**: Use the Read tool with specific line ranges from the index
-4. **Don't expand everything**: Only load content required for the current step
-
-**Example expansion**:
-```
-# To get the discovery template
-Read: resources/patterns/discovery-templates.md (lines from PTN-DIST-1)
-
-# To understand question workflow
-Read: resources/tools/interactive-questions-tool.md (lines from TLS-IQ-3)
-```
+The brain returns ranked chunks from indexed markdown files. Use the top results to inform execution.
 
 ---
 
@@ -304,9 +265,6 @@ Read: resources/tools/interactive-questions-tool.md (lines from TLS-IQ-3)
 
 | Resource                       | Purpose                                |
 | ------------------------------ | -------------------------------------- |
-| `resources/skills/_index.md`      | Index of skills with reference codes   |
-| `resources/patterns/_index.md`    | Index of patterns with reference codes |
-| `resources/tools/_index.md`       | Index of tools with reference codes    |
 | `discovery-skill.md`          | Skill that executes the discovery      |
 | `discovery-patterns.md`       | Rules and patterns for discovery       |
 | `discovery-templates.md`      | Document templates                     |

package/.claude/commands/execute-plan.md

@@ -349,67 +349,18 @@ Execution Complete!
 5. Final build and test verification
 6. Auto-archive plan and discovery to flow/archive/
 
----
+## Context Loading
+
+This command uses the **brain index** for context retrieval. Before executing, query the project brain for relevant documentation:
+
+**Queries**:
+- `planflow-ai state-query "phase execution" --scope resources`
+- `planflow-ai state-query "wave execution" --scope resources`
+- `planflow-ai state-query "phase isolation" --scope resources`
+- `planflow-ai state-query "per-task verification" --scope resources`
+- `planflow-ai state-query "atomic commits" --scope resources`
 
-## Context Optimization
-
-This command uses hierarchical context loading to reduce context consumption. Instead of loading full files, load indexes first and expand specific sections on-demand.
-
-### Recommended Loading Order
-
-1. **Always load first**: This command file (`commands/execute-plan.md`)
-2. **Load indexes**: Load `_index.md` files for relevant folders
-3. **Expand on-demand**: Use reference codes to load specific sections when needed
-
-### Index Files for Plan Execution
-
-| Index | When to Load |
-|-------|--------------|
-| `resources/skills/_index.md` | To understand execution workflow |
-| `resources/core/_index.md` | For complexity scoring reference |
-| `resources/tools/_index.md` | When switching to Plan mode |
-
-### Reference Codes for Plan Execution
-
-| Code | Description | When to Expand |
-|------|-------------|----------------|
-| SKL-EXEC-2 | Critical rules (build, DB) | Need build/DB command restrictions |
-| SKL-EXEC-4 | Analyze complexity | Determining execution strategy |
-| SKL-EXEC-6 | Execute phase with Plan mode | Running a specific phase |
-| SKL-EXEC-8 | Phase-boundary compaction | Compacting between phases |
-| SKL-EXEC-9 | Handle tests phase | Executing the tests phase |
-| SKL-EXEC-10 | Build and test verification | Final verification step |
-| SKL-EXEC-11 | Complexity-based behavior | Need low/medium/high behavior details |
-| SKL-EXEC-12 | Error handling | Build/test failure or cancellation |
-| COR-CS-1 | Complexity scoring table | Interpreting phase complexity |
-| TLS-PLN-1 | Plan mode switching | Before each phase |
-| TLS-PLN-2 | Plan mode workflow | Presenting phase details |
-| COR-CG-1 | Compaction guide purpose | When compacting at phase boundaries |
-| COR-CG-2 | Preserve rules | Crafting compact summary — what to keep |
-| COR-CG-3 | Discard rules | Crafting compact summary — what to drop |
-| COR-CG-4 | Compact summary template | Structuring compact instructions |
-| COR-PI-1 | Phase isolation architecture | Understanding isolated sub-agent flow |
-| COR-PI-2 | Sub-agent context template | Preparing focused prompt for sub-agent |
-| COR-PI-3 | Return format schema | Parsing sub-agent JSON response |
-| COR-PI-4 | Coordinator processing rules | Handling success/failure/partial returns |
-| COR-WAVE-1 | Wave execution architecture and dependency syntax | Need wave execution architecture or dependency declaration syntax |
-| COR-WAVE-2 | Wave grouping algorithm (topological sort) | Need wave grouping algorithm or backward compatibility rules |
-| COR-WAVE-3 | Parallel spawning rules and wave summary format | Need parallel spawning rules or wave execution summary format |
-| COR-WAVE-4 | Wave coordinator behavior and failure handling | Need wave coordinator behavior, file conflict detection, or failure handling |
-| COR-WAVE-5 | Wave execution configuration and interaction matrix | Need wave execution configuration, interaction matrix, or aggregation rules |
-| COR-PTV-1 | Per-task verification architecture and verify tag syntax | Need verification system overview or `<verify>` tag parsing rules |
-| COR-PTV-2 | Debug sub-agent prompt template and return schema | Need debug sub-agent configuration or diagnosis JSON format |
-| COR-PTV-3 | Verification loop flow and retry behavior | Need verification loop details or retry/escalation rules |
-| COR-PTV-4 | Task verifications JSON return field schema | Need `task_verifications` array format or field descriptions |
-
-### Expansion Instructions
-
-When executing this command:
-
-1. **Start with indexes**: Read `resources/skills/_index.md` and `resources/core/_index.md`
-2. **Identify needed codes**: Based on current phase, identify which codes are relevant
-3. **Expand as needed**: Use the Read tool with specific line ranges from the index
-4. **Don't expand everything**: Only load content required for the current phase
+The brain returns ranked chunks from indexed markdown files. Use the top results to inform execution.
 
 ---
 
@@ -417,9 +368,6 @@ When executing this command:
 
 | Resource                   | Purpose                           |
 | -------------------------- | --------------------------------- |
-| `resources/skills/_index.md`  | Index of skills with reference codes |
-| `resources/core/_index.md`    | Index of core rules with reference codes |
-| `resources/tools/_index.md`   | Index of tools with reference codes |
 | `per-task-verification.md` | Per-task verification system, debug sub-agents, JSON schemas |
 | `execute-plan-skill.md`   | Skill that executes the plan      |
 | `plans-patterns.md`       | Rules and patterns for plans      |

package/.claude/commands/heartbeat.md

@@ -93,19 +93,6 @@ RELATED COMMANDS:
 1. Read `flow/heartbeat.md`
 2. Display all tasks with their schedule, status, and description
 
----
-
-## Context Optimization
-
-### Reference Codes for Heartbeat
-
-| Code | Description | When to Expand |
-|------|-------------|----------------|
-| COR-HB-1 | Heartbeat file format and schedule syntax | Creating or editing heartbeat tasks |
-| COR-HB-2 | Daemon architecture and CLI commands | Starting/stopping the daemon |
-
----
-
 ## Brain Capture
 
 <!-- brain-capture
@@ -117,9 +104,20 @@ captures:
 
 ---
 
+## Context Loading
+
+This command uses the **brain index** for context retrieval. Before executing, query the project brain for relevant documentation:
+
+**Queries**:
+- `planflow-ai state-query "heartbeat daemon" --scope resources`
+- `planflow-ai state-query "scheduled tasks" --scope resources`
+
+The brain returns ranked chunks from indexed markdown files. Use the top results to inform execution.
+
+---
+
 ## Related Resources
 
 | Resource | Purpose |
 |----------|---------|
 | `resources/core/heartbeat.md` | File format rules and daemon architecture |
-| `resources/core/_index.md` | Index of core rules with reference codes |

package/.claude/commands/learn.md

@@ -76,7 +76,7 @@ TEACHING MODE (/learn about <topic>):
   Completed curricula are saved globally and reused across projects.
 
   Output: ~/plan-flow/brain/learns/{topic-kebab}.md (global)
-  Index:  ~/plan-flow/brain/learns/_index.md (LRN-* codes)
+  Index:  Indexed via brain query system (searchable with state-query)
 
 RELATED COMMANDS:
   /note            Capture meeting notes, ideas, brainstorms
@@ -248,7 +248,7 @@ Before designing the curriculum:
 
 1. **Use web search** to get up-to-date information (official docs, latest version, recent changes)
 2. **Read the project's stack** from `flow/brain/index.md` and `flow/references/tech-foundation.md`
-3. **Check existing learns** at `~/plan-flow/brain/learns/_index.md` — if the topic already exists, offer to resume, expand, or start fresh
+3. **Check existing learns** via `planflow-ai state-query "{topic}" --scope learns` — if the topic already exists, offer to resume, expand, or start fresh
 
 ### Step 3: Design an Adaptive Curriculum
 
@@ -305,7 +305,7 @@ After all steps are confirmed (or user stops early):
 
 **For general knowledge / concept:**
 1. Save to `~/plan-flow/brain/learns/{topic-kebab}.md`
-2. Auto-index with `LRN-*` codes in `~/plan-flow/brain/learns/_index.md`
+2. Auto-indexed by the brain query system (searchable via `planflow-ai state-query`)
 3. Update `flow/brain/index.md` with `## Global Learns` section
 
 **For project implementation:**
@@ -370,65 +370,15 @@ After all steps are confirmed (or user stops early):
 - [[{project-name}]]
 ```
 
-### Learns Index Template (`~/plan-flow/brain/learns/_index.md`)
+### Learns Index
 
-```markdown
-# Global Learns Index
-
-## Overview
-
-Shared learning curricula accumulated across all projects. Use reference codes to load specific sections on-demand.
-
-**Total Files**: X files
-**Reference Codes**: LRN-{ABBR}-1 through LRN-{ABBR}-N
-**Last Updated**: YYYY-MM-DD
-
----
-
-## Reference Codes
-
-### MCP (`mcp.md`)
-
-| Code | Description | Lines |
-|------|-------------|-------|
-| LRN-MCP-1 | What is MCP and why it matters | 10-35 |
-| LRN-MCP-2 | MCP server architecture | 36-70 |
-| LRN-MCP-3 | Building your first MCP server | 71-120 |
+Learns are automatically indexed by the brain query system. Query existing curricula with:
 
----
-
-## When to Expand
-
-| Code | Expand When |
-|------|-------------|
-| LRN-MCP-1 | Need to understand MCP fundamentals |
-| LRN-MCP-2 | Designing an MCP server |
-
----
-
-## Projects Using Learns
-
-| Learn | Projects |
-|-------|----------|
-| mcp | [[project-1]], [[project-2]] |
+```
+planflow-ai state-query "{topic}" --scope learns
 ```
 
-### Reference Code Convention for Learns
-
-| Learn File | Code Prefix | Example Codes |
-|---|---|---|
-| `mcp.md` | `LRN-MCP` | LRN-MCP-1, LRN-MCP-2, LRN-MCP-3 |
-| `docker.md` | `LRN-DK` | LRN-DK-1, LRN-DK-2 |
-| `graphql.md` | `LRN-GQ` | LRN-GQ-1, LRN-GQ-2 |
-| Other `<name>.md` | `LRN-XX` | Use first 2-3 consonants or unique abbreviation |
-
-### Reference Codes for Teaching
-
-| Code | Description | When to Expand |
-|------|-------------|----------------|
-| SKL-LRN-3 | Teaching mode restrictions and workflow | Starting teaching mode |
-| SKL-LRN-4 | Curriculum template and global storage | Generating curriculum |
-| SKL-LRN-5 | Learns index template and LRN-* code convention | Updating learns index |
+Learns are stored at `~/plan-flow/brain/learns/{topic-kebab}.md` and automatically discoverable via brain queries. No manual index maintenance required.
 
 ---
 
@@ -471,25 +421,6 @@ Teach step by step (adaptive: skip / deep dive / tangent / rephrase)
 Save to ~/plan-flow/brain/learns/ → Auto-index LRN-* codes → Link to project
 ```
 
----
-
-## Context Optimization
-
-### Recommended Loading Order
-
-1. **Always load first**: This command file (`commands/learn.md`)
-2. **Load indexes**: Load `_index.md` files for relevant folders
-3. **Expand on-demand**: Use reference codes to load specific sections when needed
-
-### Reference Codes for Learn
-
-| Code | Description | When to Expand |
-|------|-------------|----------------|
-| SKL-LRN-1 | Purpose, restrictions, and extraction criteria | Understanding what to extract |
-| SKL-LRN-2 | Workflow, output format, and validation | Processing and saving patterns |
-
----
-
 ## Brain Capture
 
 <!-- brain-capture
@@ -507,11 +438,20 @@ During pattern extraction, if you encounter valuable reference materials (API sp
 
 ---
 
+## Context Loading
+
+This command uses the **brain index** for context retrieval. Before executing, query the project brain for relevant documentation:
+
+**Queries**:
+- `planflow-ai state-query "learn skill" --scope resources`
+- `planflow-ai state-query "pattern extraction" --scope resources`
+
+The brain returns ranked chunks from indexed markdown files. Use the top results to inform execution.
+
+---
+
 ## Related Resources
 
 | Resource                    | Purpose                           |
 | --------------------------- | --------------------------------- |
-| `resources/skills/_index.md`   | Index of skills with reference codes |
 | `resources/skills/learn-skill.md` | Detailed skill implementation |
-| `resources/patterns/_index.md` | Index of patterns with reference codes |
-| `resources/core/_index.md`     | Index of core rules with reference codes |

package/.claude/commands/note.md

@@ -208,29 +208,15 @@ Brain entry captured!
 +------------------------------------------+
 ```
 
----
-
-## Context Optimization
-
-### Recommended Loading Order
+## Context Loading
 
-1. **Always load first**: This command file (`commands/note.md`)
-2. **Load indexes**: Load `_index.md` files for relevant folders
-3. **Expand on-demand**: Use reference codes to load specific sections when needed
+This command uses the **brain index** for context retrieval. Before executing, query the project brain for relevant documentation:
 
-### Reference Codes for Brain
+**Queries**:
+- `planflow-ai state-query "brain capture" --scope resources`
+- `planflow-ai state-query "brain patterns" --scope resources`
 
-| Code | Description | When to Expand |
-|------|-------------|----------------|
-| SKL-BR-1 | Brain skill restrictions | Understanding allowed actions |
-| SKL-BR-2 | Brain skill workflow | Processing entries |
-| SKL-BR-3 | Output format and validation | Formatting output |
-| PTN-BR-1 | Directory structure and naming | Creating brain files |
-| PTN-BR-2 | Wiki-link patterns | Creating cross-references |
-| PTN-BR-3 | Feature status lifecycle | Updating feature entries |
-| COR-BR-1 | Session start behavior | Understanding brain loading |
-| COR-BR-2 | File templates | Creating new brain files |
-| COR-BR-3 | Index management caps | Enforcing index limits |
+The brain returns ranked chunks from indexed markdown files. Use the top results to inform execution.
 
 ---
 
@@ -238,9 +224,6 @@ Brain entry captured!
 
 | Resource                    | Purpose                           |
 | --------------------------- | --------------------------------- |
-| `resources/skills/_index.md`   | Index of skills with reference codes |
-| `resources/patterns/_index.md` | Index of patterns with reference codes |
-| `resources/core/_index.md`     | Index of core rules with reference codes |
 | `brain-skill.md`           | Skill that processes brain entries |
 | `brain-patterns.md`        | File naming and link conventions  |
 | `brain-capture.md`         | Processing rules and templates    |

package/.claude/commands/review-code.md

@@ -126,57 +126,17 @@ review-code --scope staged
 review-code src/services/userService.ts
 ```
 
----
-
-## Context Optimization
-
-This command uses hierarchical context loading to reduce context consumption. Instead of loading full files, load indexes first and expand specific sections on-demand.
-
-### Recommended Loading Order
-
-1. **Always load first**: This command file (`commands/review-code.md`)
-2. **Load indexes**: Load `_index.md` files for relevant folders
-3. **Expand on-demand**: Use reference codes to load specific sections when needed
-
-### Index Files for Code Review
-
-| Index | When to Load |
-|-------|--------------|
-| `resources/skills/_index.md` | To understand review workflow |
-| `resources/patterns/_index.md` | For review patterns and templates |
-| `resources/core/_index.md` | For allowed/forbidden patterns reference |
-
-### Reference Codes for Code Review
-
-| Code | Description | When to Expand |
-|------|-------------|----------------|
-| SKL-REV-1 | Purpose and restrictions | Understanding allowed actions |
-| SKL-REV-2 | Identify changed files | Starting the review |
-| SKL-REV-3 | Determine review depth | Adaptive depth selection |
-| SKL-REV-5 | Find similar implementations | Searching for comparable code |
-| SKL-REV-7 | Pattern conflicts + verify + re-rank | Processing findings |
-| SKL-REV-8 | Generate review document | Creating the output file |
-| SKL-REV-9 | Severity and conflict resolution | Severity levels and resolution options |
-| PTN-REV-1 | Review document structure | Creating review output |
-| COR-AP-1 | Allowed patterns overview | Checking pattern compliance |
-| COR-FP-1 | Forbidden patterns overview | Identifying anti-patterns |
-| COR-MA-1 | Multi-agent subagent definitions | Deep mode parallel review setup |
-| COR-MA-2 | Coordinator dedup and merge | Deep mode result processing |
-| COR-SR-1 | Severity re-ranking algorithm | Ordering findings by impact |
-| COR-SR-2 | Finding grouping rules | Grouping related findings |
-| COR-AD-1 | Adaptive depth size detection | Determining review mode |
-| COR-AD-2 | Lightweight review mode | Changeset < 50 lines |
-| COR-AD-3 | Deep review mode | Changeset 500+ lines |
-| COR-CG-1 | Compaction guide | Load when compacting mid-review |
+## Context Loading
 
-### Expansion Instructions
+This command uses the **brain index** for context retrieval. Before executing, query the project brain for relevant documentation:
 
-When executing this command:
+**Queries**:
+- `planflow-ai state-query "code review workflow" --scope resources`
+- `planflow-ai state-query "adaptive depth" --scope resources`
+- `planflow-ai state-query "severity ranking" --scope resources`
+- `planflow-ai state-query "multi-agent review" --scope resources`
 
-1. **Start with indexes**: Read `resources/skills/_index.md` and `resources/patterns/_index.md`
-2. **Identify needed codes**: Based on detected language/framework, expand relevant patterns
-3. **Expand as needed**: Use the Read tool with specific line ranges from the index
-4. **Don't expand everything**: Only load patterns relevant to the files being reviewed
+The brain returns ranked chunks from indexed markdown files. Use the top results to inform execution.
 
 ---
 
@@ -184,9 +144,6 @@ When executing this command:
 
 | Resource                       | Purpose                                |
 | ------------------------------ | -------------------------------------- |
-| `resources/skills/_index.md`      | Index of skills with reference codes   |
-| `resources/patterns/_index.md`    | Index of patterns with reference codes |
-| `resources/core/_index.md`        | Index of core rules with reference codes |
 | `review-code-skill.md`        | Skill that executes the review         |
 | `review-pr-patterns.md`       | Review patterns and guidelines         |