planflow-ai 1.3.5 → 1.4.3

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/resume-work.md

@@ -0,0 +1,261 @@
+# Resume Work
+
+## Command Description
+
+This command reads `flow/STATE.md` and reconstructs full session context after a context reset (compaction, new session, crash). It identifies the active work, reads the relevant plan/discovery file, and outputs a structured summary that puts the LLM back in context.
+
+**Output**: Structured context summary displayed in chat — no files created or modified.
+
+---
+
+## Help
+
+**If the user invokes this command with `-help`, display only this section and stop:**
+
+```
+/resume-work - Resume Work from Saved State
+
+DESCRIPTION:
+  Reads flow/STATE.md and reconstructs session context after a context
+  reset. Identifies active work, reads relevant plan files, and outputs
+  a structured summary to resume where you left off.
+
+USAGE:
+  /resume-work
+  /resume-work -help
+
+ARGUMENTS:
+  None — reads STATE.md automatically.
+
+EXAMPLES:
+  /resume-work
+
+OUTPUT:
+  Displays structured context summary with:
+  - Active skill and plan
+  - Current phase and task
+  - Decisions made so far
+  - Blockers encountered
+  - Files modified
+  - Next action to take
+
+WORKFLOW:
+  1. Validates flow/STATE.md exists
+  2. Reads and parses STATE.md
+  3. Checks staleness (warns if >24h old)
+  4. Reads active plan file (if any)
+  5. Identifies next task/phase
+  6. Outputs structured context summary
+
+RELATED COMMANDS:
+  /execute-plan    Continue executing a plan
+  /flow            Check flow configuration
+```
+
+---
+
+## Critical Rules
+
+| Rule | Description |
+|------|-------------|
+| **Read-Only** | This command does NOT create, modify, or delete any files |
+| **No Auto-Chaining** | After presenting the summary, STOP and wait for user (unless autopilot ON) |
+| **No Code Execution** | Do NOT run build, test, or any implementation commands |
+| **STATE.md Required** | If STATE.md doesn't exist, inform the user — do NOT create it |
+| **Plan File is Truth** | If STATE.md references a plan, read the plan file for authoritative task status |
+
+---
+
+## Instructions
+
+### Step 1: Validate STATE.md Exists
+
+Check if `flow/STATE.md` exists.
+
+**If it does NOT exist**:
+```markdown
+No active session state found (`flow/STATE.md` does not exist).
+
+This means either:
+- No skill was in progress when the session ended
+- The previous skill completed successfully and cleared its state
+
+Use `/execute-plan`, `/discovery-plan`, or another command to start new work.
+```
+**STOP** — do not proceed.
+
+---
+
+### Step 2: Read and Parse STATE.md
+
+Read `flow/STATE.md` and extract:
+- **Active Skill**: The skill that was running
+- **Active Plan**: Path to the plan file being executed
+- **Current Phase**: Phase number and name
+- **Current Task**: The specific task in progress
+- **Completed Phases**: List of completed phases with outcomes
+- **Decisions**: Decisions made during the session
+- **Blockers**: Issues encountered and their status
+- **Files Modified**: Files changed during the session
+- **Next Action**: What to do immediately
+
+---
+
+### Step 3: Staleness Check
+
+Parse the `**Updated**` timestamp from STATE.md.
+
+**If the timestamp is more than 24 hours old**:
+```markdown
+> **Stale State Warning**: STATE.md was last updated {time_ago} ({timestamp}).
+> The session state may be outdated.
+>
+> Options:
+> 1. **Resume anyway** — continue from where STATE.md left off
+> 2. **Start fresh** — delete STATE.md and begin new work
+```
+
+Wait for user response before proceeding.
+
+**If the timestamp is within 24 hours**: Continue silently.
+
+---
+
+### Step 4: Read Active Plan File
+
+If STATE.md references an active plan (`Active Plan` is not "none"):
+1. Read the plan file
+2. Cross-reference completed phases in STATE.md with task checkboxes in the plan
+3. Identify the next uncompleted task
+
+If the plan file doesn't exist, note this as a warning.
+
+---
+
+### Step 5: Output Context Summary
+
+Present the reconstructed context:
+
+```markdown
+## Session Resumed
+
+**Active Skill**: {skill name}
+**Active Plan**: `{plan file path}`
+**Progress**: Phase {N} of {total} — {phase name}
+
+### Completed Phases
+{list of completed phases with outcomes}
+
+### Decisions Made
+{list of decisions with rationale}
+
+### Blockers
+{list of blockers with status}
+
+### Files Modified
+{list of files changed}
+
+### Next Action
+> {next action from STATE.md}
+
+---
+
+Ready to continue. Run the active skill command or describe what you'd like to do next.
+```
+
+---
+
+### Step 6: Stop and Wait
+
+After presenting the summary, **STOP**. Do not auto-invoke any commands.
+
+---
+
+## Flow Diagram
+
+```
++------------------------------------------+
+|         /resume-work COMMAND             |
++------------------------------------------+
+                    |
+                    v
++------------------------------------------+
+| Step 1: Validate STATE.md Exists         |
+| - If missing: inform user and stop       |
++------------------------------------------+
+                    |
+                    v
++------------------------------------------+
+| Step 2: Read and Parse STATE.md          |
+| - Extract all sections                   |
++------------------------------------------+
+                    |
+                    v
++------------------------------------------+
+| Step 3: Staleness Check                  |
+| - Warn if >24h old                       |
+| - Ask user: resume or start fresh        |
++------------------------------------------+
+                    |
+                    v
++------------------------------------------+
+| Step 4: Read Active Plan File            |
+| - Cross-reference with STATE.md          |
+| - Identify next task                     |
++------------------------------------------+
+                    |
+                    v
++------------------------------------------+
+| Step 5: Output Context Summary           |
+| - Structured markdown with all state     |
++------------------------------------------+
+                    |
+                    v
++------------------------------------------+
+| Step 6: Stop and Wait                    |
+| - User decides next action               |
++------------------------------------------+
+```
+
+---
+
+## STATE.md Updates
+
+This command does NOT update STATE.md. It is read-only.
+
+---
+
+## Brain Capture
+
+After resume completes, append a brain-capture block:
+
+```
+<!-- brain-capture
+skill: resume-work
+feature: [feature from active plan]
+status: completed
+data:
+  active_skill: [skill being resumed]
+  active_plan: [plan file path]
+  phase_resumed: [phase number]
+  staleness_hours: [hours since last update]
+-->
+```
+
+---
+
+## Tasklist Updates
+
+This command does NOT update the tasklist. It is read-only.
+
+---
+
+## Related Resources
+
+| Resource | Purpose |
+|----------|---------|
+| `resources/skills/resume-work-skill.md` | Skill implementation details |
+| `resources/core/compaction-guide.md` | What to preserve during compaction |
+| `resources/core/session-scratchpad.md` | Complementary session notes |
+| `/execute-plan` command | Continue plan execution |
+| `/flow` command | Check flow configuration |

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 |
+## Context Loading
 
-### Reference Codes for Code Review
+This command uses the **brain index** for context retrieval. Before executing, query the project brain for relevant documentation:
 
-| 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 |
+**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`
 
-### Expansion Instructions
-
-When executing this command:
-
-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         |
 
@@ -225,6 +182,17 @@ Run any of these to build structured understanding before or after merging.
 
 ---
 
+## STATE.md Updates
+
+Update `flow/STATE.md` at these transition points to enable session resumability.
+
+| Transition Point | Action |
+|-----------------|--------|
+| **Review start** | Create `flow/STATE.md` with `Active Skill: review-code`, `Active Plan: none`, `Current Phase: none`, `Current Task: reviewing {scope}`, `Next Action: Analyze changes and generate review` |
+| **Review complete** | Delete `flow/STATE.md` (skill is done, no state to preserve) |
+
+---
+
 ## Brain Capture
 
 After code review completes, append a brain-capture block. See `.claude/resources/core/brain-capture.md` for processing rules.

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

@@ -120,60 +120,17 @@ review-pr https://github.com/org/repo/pull/123
 review-pr https://dev.azure.com/org/project/_git/repo/pullrequest/456
 ```
 
----
+## Context Loading
+
+This command uses the **brain index** for context retrieval. Before executing, query the project brain for relevant documentation:
 
-## 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-pr.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 PR Review
-
-| Index | When to Load |
-|-------|--------------|
-| `resources/skills/_index.md` | To understand review workflow |
-| `resources/tools/_index.md` | For authentication tool |
-| `resources/patterns/_index.md` | For review patterns |
-| `resources/core/_index.md` | For allowed/forbidden patterns |
-
-### Reference Codes for PR Review
-
-| Code | Description | When to Expand |
-|------|-------------|----------------|
-| SKL-PR-1 | Purpose and restrictions | Understanding allowed actions |
-| SKL-PR-2 | Authenticate for PR access | Setting up authentication |
-| SKL-PR-3 | Fetch PR info + determine depth | Getting PR data and review mode |
-| SKL-PR-5 | Analyze + verify + re-rank | Processing findings |
-| SKL-PR-6 | Generate review document | Creating the output file |
-| SKL-PR-7 | Output template | Review document structure |
-| SKL-PR-8 | Fix complexity scoring | Severity and complexity details |
-| SKL-PR-9 | Link format (GitHub/Azure DevOps) | Platform-specific link formats |
-| TLS-AUTH-1 | Auth tool configuration | Setting up authentication |
-| TLS-AUTH-2 | Authentication workflow | Authenticating to platform |
-| PTN-PR-1 | PR review patterns | 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 |
-
-### Expansion Instructions
-
-When executing this command:
-
-1. **Start with indexes**: Read `resources/skills/_index.md` and `resources/tools/_index.md`
-2. **Expand auth first**: Load TLS-AUTH-* codes for authentication
-3. **Then expand review patterns**: Load PTN-PR-* codes for review structure
-4. **Don't expand everything**: Only load patterns relevant to the PR being reviewed
+**Queries**:
+- `planflow-ai state-query "PR review workflow" --scope resources`
+- `planflow-ai state-query "adaptive depth" --scope resources`
+- `planflow-ai state-query "severity ranking" --scope resources`
+- `planflow-ai state-query "PR authentication" --scope resources`
+
+The brain returns ranked chunks from indexed markdown files. Use the top results to inform execution.
 
 ---
 
@@ -181,10 +138,6 @@ When executing this command:
 
 | Resource                       | Purpose                                |
 | ------------------------------ | -------------------------------------- |
-| `resources/skills/_index.md`      | Index of skills with reference codes   |
-| `resources/tools/_index.md`       | Index of tools 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-pr-skill.md`          | Skill that executes the review         |
 | `auth-pr-tool.md`             | Authentication tool for PR platforms   |
 | `review-pr-patterns.md`       | Review patterns and guidelines         |
@@ -225,6 +178,17 @@ Run any of these to build structured understanding before or after merging.
 
 ---
 
+## STATE.md Updates
+
+Update `flow/STATE.md` at these transition points to enable session resumability.
+
+| Transition Point | Action |
+|-----------------|--------|
+| **Review start** | Create `flow/STATE.md` with `Active Skill: review-pr`, `Active Plan: none`, `Current Phase: none`, `Current Task: reviewing PR #{number}`, `Next Action: Authenticate, fetch PR, and analyze` |
+| **Review complete** | Delete `flow/STATE.md` (skill is done, no state to preserve) |
+
+---
+
 ## Brain Capture
 
 After PR review completes, append a brain-capture block. See `.claude/resources/core/brain-capture.md` for processing rules.