planflow-ai 1.1.2 → 1.1.4

package/.claude/commands/brain.md

@@ -63,9 +63,6 @@ RELATED COMMANDS:
 
 ---
 
-> **AGENT_PROFILE: write-restricted**
-> See `.claude/resources/core/agent-profiles.md` for tool access rules.
-
 ## Critical Rules
 
 | Rule                     | Description                                              |

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

@@ -55,18 +55,12 @@ RELATED COMMANDS:
 
 ---
 
-> **MODE: Research**
-> Explore before concluding. Read 3x more than you write. Prefer Read/Grep/Glob/WebSearch tools.
-> Ask clarifying questions when uncertain. Don't jump to implementation.
-
-> **AGENT_PROFILE: read-only**
-> See `.claude/resources/core/agent-profiles.md` for tool access rules.
-
 ## Critical Rules
 
 | Rule                     | Description                                              |
 | ------------------------ | -------------------------------------------------------- |
 | **No Auto-Chaining**     | NEVER auto-invoke /discovery-plan - user must invoke it  |
+| **File Only**            | Save the `.md` file and report its path. Do NOT show full content in chat. |
 | **Complete and Stop**    | After presenting results, STOP and wait for user         |
 
 ---
@@ -122,27 +116,30 @@ See: `.claude/resources/skills/create-contract-skill.md`
 
 ---
 
-### Step 4: Present Results
+### Step 4: Save File and Stop
 
-After the skill completes, confirm file creation:
+After the skill completes:
 
-```markdown
-Contract Created!
+1. **Save the contract document** to `flow/contracts/<service_name>_contract.md`
+2. **Report only the file path** — do NOT display the full contract content in chat
+3. **STOP** — do NOT auto-invoke `/discovery-plan`
 
-**Deliverable**: `flow/contracts/<service_name>_contract.md`
+**Output to the user** (this is the ONLY thing to show):
 
-**Summary**:
-- X endpoints documented
-- Authentication: [method]
-- Error handling documented
+```markdown
+Contract created.
 
-**Next Steps** (user must invoke manually):
-1. Review the contract above
-2. Request any refinements
-3. When ready, invoke `/discovery-plan @flow/contracts/<service_name>_contract.md`
+**Created**: `flow/contracts/<service_name>_contract.md`
+
+Next: review the file, then run `/discovery-plan` when ready.
 ```
 
-**CRITICAL**: This command is now complete. Do NOT auto-invoke `/discovery-plan`. Wait for the user to explicitly invoke it.
+⚠️ **CRITICAL**: After saving the file, the command is DONE. Do NOT:
+- Show the full contract content in chat
+- Auto-invoke `/discovery-plan`
+- Offer to start discovery or planning
+
+The user will read the `.md` file themselves and decide when to proceed.
 
 ---
 
@@ -175,9 +172,10 @@ Contract Created!
                     |
                     v
 +------------------------------------------+
-| Step 4: Present Results                  |
-| - Show summary                           |
-| - Link to /discovery-plan command        |
+| Step 4: Save File and Stop               |
+| - Save .md file to flow/contracts/       |
+| - Report file path only                  |
+| - STOP (no discovery, no plan)           |
 +------------------------------------------+
 ```
 
@@ -248,47 +246,3 @@ When executing this command:
 | `interactive-questions-tool.md` | Interactive Questions UI workflow    |
 | `/discovery-plan` command      | Create discovery from contract         |
 | `/create-plan` command         | Create plan from discovery             |
-
----
-
-## Compaction Suggestion
-
-After contract creation completes, suggest context cleanup if the contract was complex (> 5 endpoints):
-
-> Contract created. Consider running `/compact` to free context before the next task.
-
-Skip if autopilot is ON.
-
----
-
-## Brain Capture
-
-After contract creation completes, append a brain-capture block. See `.claude/resources/core/brain-capture.md` for processing rules.
-
-**Capture the following**:
-
-```
-<!-- brain-capture
-skill: create-contract
-feature: [service name]
-status: completed
-data:
-  service_name: [API/service name]
-  endpoints_documented: [count]
-  auth_type: [detected auth type]
-  contract_doc: [path to contract document]
--->
-```
-
-Update `flow/brain/features/[service-name].md` with contract context and update `flow/brain/index.md`.
-
----
-
-## Resource Capture
-
-During this skill's execution, watch for valuable reference materials worth preserving. See `.claude/resources/core/resource-capture.md` for capture rules, file format, and naming conventions.
-
-At natural break points, if you encounter information that could be useful for future development (API specs, architecture notes, config references, domain knowledge, etc.), ask the user: "I found something that could be useful for future reference: _{brief description}_. Should I save it to `flow/resources/`?"
-
-Only save if the user approves. Do not re-ask if declined.
-

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

@@ -64,19 +64,13 @@ RELATED COMMANDS:
 > - **If YES**: Autopilot is ON. After creating the plan and getting user approval, **auto-proceed** to `/execute-plan` with the plan output. Do NOT wait for manual invocation.
 > - **If NO**: Follow the standard rules below (stop and wait for user).
 
-> **MODE: Research**
-> Explore before concluding. Read 3x more than you write. Prefer Read/Grep/Glob/WebSearch tools.
-> Ask clarifying questions when uncertain. Don't jump to implementation.
-
-> **AGENT_PROFILE: read-only**
-> See `.claude/resources/core/agent-profiles.md` for tool access rules.
-
 ## Critical Rules
 
 | Rule                     | Description                                              |
 | ------------------------ | -------------------------------------------------------- |
 | **Discovery Required**   | NEVER create a plan without a discovery document. If none exists, run `/discovery-plan` first. No exceptions. |
 | **No Auto-Chaining**     | NEVER auto-invoke /execute-plan - user must invoke it (unless autopilot ON) |
+| **File Only**            | Save the `.md` file and report its path. Do NOT show full content in chat. |
 | **Complete and Stop**    | After presenting results, STOP and wait for user (unless autopilot ON) |
 
 ---
@@ -141,50 +135,31 @@ See: `.claude/resources/skills/create-plan-skill.md`
 
 ---
 
-### Step 5: Present Results
+### Step 5: Save File and Stop
 
-After the skill completes, confirm file creation and summarize:
+After the skill completes:
 
-```markdown
-Plan Created!
+1. **Save the plan document** to `flow/plans/plan_<feature>_v<version>.md`
+2. **Report only the file path** — do NOT display the full plan content in chat
+3. **STOP** — do NOT execute the plan, do NOT offer to build
 
-**Deliverable**: `flow/plans/plan_<feature>_v<version>.md`
+**Output to the user** (this is the ONLY thing to show):
 
-**Summary**:
-- X phases created
-- Total complexity: XX/XX
-- Highest complexity: Phase X at Y/10
-```
+```markdown
+Plan created.
 
-**CRITICAL — Check autopilot mode BEFORE presenting next steps:**
-
-1. **Check if `flow/.autopilot` exists**
-2. **If autopilot is ON**: Do NOT show "Next Steps" or "invoke manually". Instead, use `AskUserQuestion` to ask for plan approval, then **immediately auto-proceed** to `/execute-plan` with the plan file. Do NOT stop. Do NOT wait for the user to manually invoke `/execute-plan`.
-
-```typescript
-// When autopilot is ON, ask for approval then auto-proceed:
-AskUserQuestion({
-  questions: [{
-    question: "Plan is ready. Approve to proceed with execution?",
-    header: "Plan",
-    options: [
-      { label: "Approve and execute", description: "Start executing the plan now" },
-      { label: "Refine first", description: "Let me suggest changes to the plan before executing" }
-    ],
-    multiSelect: false
-  }]
-})
-// If approved → immediately invoke /execute-plan (do NOT stop)
+**Created**: `flow/plans/plan_<feature>_v<version>.md`
+
+Next: review the file, then run `/execute-plan` when ready.
 ```
 
-3. **If autopilot is OFF**: Show next steps and stop:
+⚠️ **CRITICAL**: After saving the file, the command is DONE. Do NOT:
+- Show the full plan content in chat
+- Auto-invoke `/execute-plan`
+- Offer to start building or implementing
+- Show implementation steps or code
 
-```markdown
-**Next Steps**:
-1. Review the plan above
-2. Request any refinements
-3. When ready, invoke `/execute-plan @flow/plans/plan_<feature>_v<version>.md`
-```
+The user will read the `.md` file themselves and decide when to proceed.
 
 ---
 
@@ -224,9 +199,10 @@ AskUserQuestion({
                     |
                     v
 +------------------------------------------+
-| Step 5: Present Results                  |
-| - Show summary                           |
-| - Link to /execute-plan command          |
+| Step 5: Save File and Stop               |
+| - Save .md file to flow/plans/           |
+| - Report file path only                  |
+| - STOP (no execute, no build)            |
 +------------------------------------------+
 ```
 
@@ -299,63 +275,3 @@ When executing this command:
 | `complexity-scoring.md`    | Complexity scoring system         |
 | `/discovery-plan` command   | Run discovery first               |
 | `/execute-plan` command     | Execute the created plan          |
-
----
-
-## Compaction Suggestion
-
-After plan creation completes, suggest context cleanup:
-
-> Plan created. Consider running `/compact` before execution to maximize available context for the implementation phases.
-
-Only suggest if the plan has > 3 phases. Skip if autopilot is ON.
-
----
-
-## Brain Capture
-
-After plan creation completes successfully, append a brain-capture block. See `.claude/resources/core/brain-capture.md` for processing rules.
-
-**Capture the following**:
-
-```
-<!-- brain-capture
-skill: create-plan
-feature: [feature name]
-status: completed
-data:
-  phase_count: [number of phases]
-  total_complexity: [sum of complexity scores]
-  highest_phase: [phase name with highest score]
-  discovery_link: [[discovery-feature-name]]
-  plan_doc: [path to plan document]
--->
-```
-
-Update `flow/brain/features/[feature-name].md` with plan details and link to discovery entry.
-
----
-
-## Resource Capture
-
-During this skill's execution, watch for valuable reference materials worth preserving. See `.claude/resources/core/resource-capture.md` for capture rules, file format, and naming conventions.
-
-At natural break points, if you encounter information that could be useful for future development (API specs, architecture notes, config references, domain knowledge, etc.), ask the user: "I found something that could be useful for future reference: _{brief description}_. Should I save it to `flow/resources/`?"
-
-Only save if the user approves. Do not re-ask if declined.
-
----
-
-## Handoff
-
-### Consumption
-
-Before creating the plan, check for `flow/handoffs/handoff_<feature>_discovery_to_plan.md` (or `handoff_<feature>_review_to_plan.md` for bugfix workflow). If it exists, read it silently and use its focus guidance to inform plan structure. If it doesn't exist, proceed normally (backward compatible).
-
-### Production
-
-After the plan is created, produce a handoff for the execution step.
-
-**Output**: `flow/handoffs/handoff_<feature>_plan_to_execute.md`
-
-Include: feature name, workflow type, phase count, total complexity, highest complexity phase, plan and discovery paths, and focus guidance for execution.

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

@@ -18,13 +18,6 @@ This command creates a discovery document for gathering and clarifying requireme
 > - **If YES**: Autopilot is ON. After completing discovery and user Q&A, **auto-proceed** to `/create-plan` with the discovery output. Do NOT ask "Would you like to proceed?" - just continue.
 > - **If NO**: Follow the standard rules below (stop and wait for user).
 
-> **MODE: Research**
-> Explore before concluding. Read 3x more than you write. Prefer Read/Grep/Glob/WebSearch tools.
-> Ask clarifying questions when uncertain. Don't jump to implementation.
-
-> **AGENT_PROFILE: read-only**
-> See `.claude/resources/core/agent-profiles.md` for tool access rules.
-
 > ⚠️ **IMPORTANT - DISCOVERY ONLY**
 >
 > This command ONLY creates a discovery document. It does NOT:
@@ -73,9 +66,8 @@ WORKFLOW:
   4. Documents requirements (FR, NFR, Constraints)
   5. Proposes high-level approach (no code)
   6. Creates discovery document for review
-  7. Asks user if they want to proceed, refine, or stop
-  8. Supports iterative refinement (max 3 rounds)
-  9. Waits for user confirmation before proceeding
+  7. Asks user if they want to proceed to /create-plan
+  8. Waits for user confirmation before proceeding
 
 RECOMMENDED MODEL:
   Claude Opus 4.6 or Sonnet 4.5 for best results
@@ -94,7 +86,7 @@ These rules are mandatory. For detailed patterns and guidelines, see `.claude/re
 | Rule                     | Description                                              |
 | ------------------------ | -------------------------------------------------------- |
 | **No Code**              | NEVER write, edit, or generate code during discovery     |
-| **Only Markdown Output** | The ONLY deliverable is the discovery markdown file      |
+| **Only Markdown Output** | The ONLY deliverable is the discovery markdown file. Do NOT display it in chat. |
 | **Ask Questions**        | When in doubt, ask - don't assume                        |
 | **Read First**           | Read all referenced documents before asking questions    |
 | **High-Level Only**      | Technical considerations are conceptual, not code        |
@@ -103,6 +95,7 @@ These rules are mandatory. For detailed patterns and guidelines, see `.claude/re
 | **No Auto-Execution**    | Do NOT auto-invoke commands without user confirmation (unless autopilot ON) |
 | **NO PLANNING**          | Do NOT create implementation plans during discovery      |
 | **NO EXECUTION**         | Do NOT execute any implementation steps                  |
+| **File Only**            | Save the `.md` file and report its path. Do NOT show full content in chat. |
 
 ---
 
@@ -129,24 +122,6 @@ To start the discovery process, I need to understand:
 
 ---
 
-### Step 1.5: Search for Existing Solutions
-
-**Before recommending implementation**, check if the problem is already solved:
-
-1. **Project code**: Use Grep/Glob to search for existing implementations, similar patterns, or utilities that already address part of the requirement
-2. **Package registries**: Use WebSearch to check npm (for JS/TS projects) or PyPI (for Python projects) for established libraries
-   - Search: `"{problem description} npm package"` or `"{problem description} python library"`
-   - Evaluate: maintenance status (last publish date), weekly downloads, compatibility with project stack
-3. **Document findings** in an "Existing Solutions Analysis" section in the discovery document
-
-**Decision criteria**:
-- If an existing library covers **>80%** of the need → recommend using it instead of building from scratch
-- If **<80%** → note what it covers and what custom work remains
-
-**Graceful degradation**: If WebSearch is unavailable, skip registry search and note "Package registry search skipped — WebSearch unavailable" in the discovery document. Always perform the project code search.
-
----
-
 ### Step 2: Extract Feature Name
 
 From the user input, extract or derive a feature name for the discovery document.
@@ -180,81 +155,37 @@ The skill will:
 6. Identify technical considerations
 7. Propose high-level approach
 8. Document risks and unknowns
-9. Generate discovery document
-10. Support iterative refinement (max 3 rounds) if user requests it
-11. Ask user if they want to proceed to /create-plan
-12. Wait for user confirmation before proceeding
+9. Generate discovery document and save to `flow/discovery/`
 
 See: `.claude/resources/skills/discovery-skill.md`
 
 ---
 
-### Step 5: Present Results
+### Step 5: Save File and Stop
 
-After the skill completes, present the discovery document to the user:
+After the skill completes:
 
-```markdown
-Discovery Complete!
+1. **Save the discovery document** to `flow/discovery/discovery_<feature>_v<version>.md`
+2. **Report only the file path** — do NOT display the full document content in chat
+3. **STOP** — do NOT create a plan, do NOT offer to build, do NOT show implementation steps
 
-**Summary**:
-- X functional requirements gathered
-- X non-functional requirements identified
-- X risks documented
-- X questions resolved
+**Output to the user** (this is the ONLY thing to show):
 
-**Deliverable Created**: `flow/discovery/discovery_<feature>_v1.md`
+```markdown
+Discovery complete.
 
-**Next Steps**:
-1. Review the discovery document above
-2. Request any refinements or additions (if needed)
-3. Proceed to planning when ready
-```
+**Created**: `flow/discovery/discovery_<feature>_v1.md`
 
-**Now ask the user using the `AskUserQuestion` tool**:
-
-```typescript
-AskUserQuestion({
-  questions: [{
-    question: "Would you like me to proceed with creating the implementation plan?",
-    header: "Next step",
-    options: [
-      { label: "Yes, create plan", description: "I'll invoke /create-plan with the discovery document" },
-      { label: "No, review first", description: "You can review the discovery and invoke /create-plan when ready" },
-      { label: "Refine discovery", description: "Iteratively refine the discovery document (max 3 rounds)" }
-    ],
-    multiSelect: false
-  }]
-})
+Next: review the file, then run `/create-plan` when ready.
 ```
 
-⚠️ **WAIT for user response before proceeding**
-
-Do NOT auto-invoke `/create-plan` without user confirmation.
-
-#### Refinement Loop (when "Refine discovery" is selected)
-
-When the user selects "Refine discovery", invoke the discovery skill's **Step 9: Refinement Loop**:
-
-1. **Accept feedback**: Ask user what areas need adjustment (requirements, approach, scope, risks)
-2. **Follow-up questions**: Ask 1-3 targeted questions about the refinement areas only
-3. **Update document**: Modify the discovery document in-place, add/update Refinement History section
-4. **Re-present**: Show the updated document and offer the same 3 options again
-5. **Round tracking**: Track refinement round count (max 3). After 3 rounds, only offer "Yes, create plan" and "No, review first" — the "Refine discovery" option is removed
-
-```typescript
-// After 3 refinement rounds, remove the refine option:
-AskUserQuestion({
-  questions: [{
-    question: "Discovery refined 3 times (maximum). Would you like to proceed?",
-    header: "Next step",
-    options: [
-      { label: "Yes, create plan", description: "I'll invoke /create-plan with the discovery document" },
-      { label: "No, stop here", description: "You can review and invoke /create-plan manually when ready" }
-    ],
-    multiSelect: false
-  }]
-})
-```
+⚠️ **CRITICAL**: After saving the file, the command is DONE. Do NOT:
+- Show the full discovery document content in chat
+- Create or suggest an implementation plan
+- Offer to build or execute anything
+- Auto-invoke `/create-plan`
+
+The user will read the `.md` file themselves and decide when to proceed.
 
 ---
 
@@ -288,10 +219,10 @@ AskUserQuestion({
                     |
                     v
 +------------------------------------------+
-| Step 5: Present Results                  |
-| - Show summary to user                   |
-| - Allow refinement                       |
-| - Link to /create-plan command           |
+| Step 5: Save File and Stop               |
+| - Save .md file to flow/discovery/       |
+| - Report file path only                  |
+| - STOP (no plan, no build)               |
 +------------------------------------------+
 ```
 
@@ -374,60 +305,3 @@ Read: resources/tools/interactive-questions-tool.md (lines from TLS-IQ-3)
 | `discovery-templates.md`      | Document templates                     |
 | `interactive-questions-tool.md` | Interactive Questions UI workflow    |
 | `/create-plan` command         | Creates plan from discovery document   |
-
----
-
-## Compaction Suggestion
-
-After discovery completes, suggest context cleanup:
-
-> Discovery complete. Consider running `/compact` before creating a plan to free context for the planning phase.
-
-Only suggest if the discovery was substantial (> 5 requirements gathered). Skip if autopilot is ON (context will be managed automatically).
-
----
-
-## Brain Capture
-
-After discovery completes successfully, append a brain-capture block. See `.claude/resources/core/brain-capture.md` for processing rules.
-
-**Capture the following**:
-
-```
-<!-- brain-capture
-skill: discovery
-feature: [feature name from discovery]
-status: completed
-data:
-  user_prompt: [original user request]
-  questions_asked: [count]
-  questions_answered: [count]
-  requirements_fr: [count of functional requirements]
-  requirements_nfr: [count of non-functional requirements]
-  discovery_doc: [path to discovery document]
--->
-```
-
-Write/update `flow/brain/features/[feature-name].md` with discovery context and update `flow/brain/index.md`.
-
----
-
-## Resource Capture
-
-During this skill's execution, watch for valuable reference materials worth preserving. See `.claude/resources/core/resource-capture.md` for capture rules, file format, and naming conventions.
-
-At natural break points, if you encounter information that could be useful for future development (API specs, architecture notes, config references, domain knowledge, etc.), ask the user: "I found something that could be useful for future reference: _{brief description}_. Should I save it to `flow/resources/`?"
-
-Only save if the user approves. Do not re-ask if declined.
-
----
-
-## Handoff Production
-
-After discovery completes, produce a handoff document for the next step. See `.claude/resources/patterns/handoff-patterns.md` [PTN-HND-1] for the template.
-
-**Output**: `flow/handoffs/handoff_<feature>_discovery_to_plan.md`
-
-Include: feature name, workflow type, requirements summary (FR/NFR/C counts), key decisions from Q&A, top risks, discovery doc path, and focus guidance for planning.
-
-Create the `flow/handoffs/` directory if it doesn't exist.

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

@@ -49,7 +49,7 @@ WORKFLOW:
      - Presents phase details for approval
      - Implements after approval
      - Updates progress in plan file
-  4. Runs build and test verification using detected language commands (ONLY at the end)
+  4. Runs npm run build && npm run test (ONLY at the end)
   5. Auto-archives plan and discovery to flow/archive/
 
 EXECUTION STRATEGIES:
@@ -79,13 +79,6 @@ RELATED COMMANDS:
 > - **If YES**: Autopilot is ON. After completing execution (build + test pass), **auto-proceed** to `/review-code`. Do NOT stop and wait.
 > - **If NO**: Follow the standard rules below (stop and wait for user).
 
-> **MODE: Dev**
-> Code first, test after. Prefer Edit/Write/Bash tools. Run build/test after changes.
-> Move efficiently. Verify with tests, not exploration.
-
-> **AGENT_PROFILE: full-access**
-> See `.claude/resources/core/agent-profiles.md` for tool access rules.
-
 ## Critical Rules
 
 | Rule                     | Description                                              |
@@ -141,21 +134,9 @@ Please run this command and let me know when it's complete.
 
 ## CRITICAL RULE: Build Verification ONLY at the End
 
-**DO NOT run the project's build command after each phase or group.**
-
-**Build and test commands MUST ONLY be executed at the very end, after ALL phases (including Tests) are complete.** Use `.claude/resources/core/tech-detection.md` to determine the correct commands for the project's language.
-
-**Structured Verification Format**: When running final verification, output:
-
-```
-VERIFICATION: [PASS/FAIL]
-Build:    [OK/FAIL - details]
-Types:    [OK/X errors]
-Tests:    [X/Y passed]
-Ready for PR: [YES/NO]
-```
+**DO NOT run `npm run build` after each phase or group.**
 
-Append this to the plan file under `## Verification Report`.
+**`npm run build` and `npm run test` MUST ONLY be executed at the very end, after ALL phases (including Tests) are complete.**
 
 ---
 
@@ -324,7 +305,6 @@ When executing this command:
 | `resources/core/_index.md`    | Index of core rules with reference codes |
 | `resources/tools/_index.md`   | Index of tools with reference codes |
 | `execute-plan-skill.md`   | Skill that executes the plan      |
-| `core/tech-detection.md`  | Language-adaptive build/test commands |
 | `plans-patterns.md`       | Rules and patterns for plans      |
 | `complexity-scoring.md`   | Complexity scoring system         |
 | `plan-mode-tool.md`       | Plan mode switching instructions  |
@@ -333,31 +313,6 @@ When executing this command:
 
 ---
 
-## Cleanup Pass (De-Sloppify)
-
-After ALL phases complete and build/tests pass, run an automatic cleanup pass to remove development artifacts. This runs before code review (in autopilot) or before archive.
-
-### Target Patterns (ONLY remove these)
-
-1. **Debug statements**: `console.log`, `console.debug`, `console.warn` used for debugging (not intentional application logging)
-2. **Commented-out code**: Code blocks that are commented out (not documentation comments or TODO/FIXME markers)
-3. **Language-behavior tests**: Test assertions that verify language or framework behavior rather than business logic (e.g., testing that `typeof` returns expected values, testing that `Array.map` works)
-4. **Redundant type checks**: Runtime type checks that duplicate compile-time TypeScript guarantees (e.g., `if (typeof x === 'string')` when `x` is already typed as `string`)
-5. **Unused imports**: Import statements added during development that are no longer referenced
-
-### Safety Protocol
-
-1. Make all cleanup changes
-2. Run the full test suite (using the detected test command)
-3. **If ANY test fails** → revert ALL cleanup changes and report: "Cleanup reverted — {N} test(s) failed after removing {description}"
-4. **If all tests pass** → report: "Cleanup: removed {X} debug statements, {Y} commented blocks, {Z} redundant tests. All tests passing."
-
-### Skip Option
-
-The cleanup pass runs by default but can be skipped. If the user requests skipping, proceed directly to archive/review.
-
----
-
 ## Brain Capture
 
 After each phase completes (and after full execution), append brain-capture blocks. See `.claude/resources/core/brain-capture.md` for processing rules.
@@ -404,18 +359,3 @@ At natural break points, if you encounter information that could be useful for f
 
 Only save if the user approves. Do not re-ask if declined.
 
----
-
-## Handoff
-
-### Consumption
-
-Before starting execution, check for `flow/handoffs/handoff_<feature>_plan_to_execute.md`. If it exists, read it silently and use its focus guidance to prioritize execution. If it doesn't exist, proceed normally (backward compatible).
-
-### Production
-
-After ALL phases complete and build/test verification passes, produce a handoff for the review step.
-
-**Output**: `flow/handoffs/handoff_<feature>_execute_to_review.md`
-
-Include: feature name, workflow type, phases completed, build/test status, plan path, and **Plan Alignment Data** — list of planned files (from plan tasks) vs actually modified files (from `git diff --name-only`), noting scope drift and missing changes.