@iloom/cli 0.6.1 → 0.7.0

package/dist/prompts/issue-prompt.txt

@@ -47,44 +47,44 @@ Use these Recap MCP tools:
 
 ---
 
-{{#IF DRAFT_PR_MODE}}
+{{#if DRAFT_PR_MODE}}
 ## Comment Routing: Draft PR Mode
 
 **IMPORTANT: This loom is using draft PR mode.**
 
-- **Read issue details** from Issue #ISSUE_NUMBER using `mcp__issue_management__get_issue`
-- **Write ALL workflow comments** to PR #DRAFT_PR_NUMBER using `type: "pr"`
+- **Read issue details** from Issue #{{ISSUE_NUMBER}} using `mcp__issue_management__get_issue`
+- **Write ALL workflow comments** to PR #{{DRAFT_PR_NUMBER}} using `type: "pr"`
 
 When calling `mcp__issue_management__create_comment`:
 ```
 {
-  number: "DRAFT_PR_NUMBER",
+  number: "{{DRAFT_PR_NUMBER}}",
   body: "your comment content",
   type: "pr"
 }
 ```
 
 This keeps all AI workflow comments on the draft PR, not the original issue.
-{{/IF DRAFT_PR_MODE}}
-{{#IF STANDARD_ISSUE_MODE}}
+{{/if}}
+{{#if STANDARD_ISSUE_MODE}}
 ## Comment Routing: Standard Issue Mode
 
-- **Read issue details** from Issue #ISSUE_NUMBER using `mcp__issue_management__get_issue`
-- **Write ALL workflow comments** to Issue #ISSUE_NUMBER using `type: "issue"`
+- **Read issue details** from Issue #{{ISSUE_NUMBER}} using `mcp__issue_management__get_issue`
+- **Write ALL workflow comments** to Issue #{{ISSUE_NUMBER}} using `type: "issue"`
 
 When calling `mcp__issue_management__create_comment`:
 ```
 {
-  number: "ISSUE_NUMBER",
+  number: "{{ISSUE_NUMBER}}",
   body: "your comment content",
   type: "issue"
 }
 ```
-{{/IF STANDARD_ISSUE_MODE}}
+{{/if}}
 
 ---
 
-{{#IF FIRST_TIME_USER}}
+{{#if FIRST_TIME_USER}}
 ## First-Time User Context
 
 This is the user's first time running through the `iloom` workflow. You have additional context about iloom to help provide comprehensive onboarding.
@@ -135,11 +135,11 @@ Settings are stored in `.iloom/settings.json` and .iloom/settings.local.json:
 
 ### Complete Documentation Reference - use this to provide answers to questions about functionality or limitations.
 
-README_CONTENT
+{{README_CONTENT}}
 
 ### Settings Schema Documentation - use this to suggest solutions to any questions that might be asked
 
-SETTINGS_SCHEMA_CONTENT
+{{SETTINGS_SCHEMA_CONTENT}}
 
 ### User Onboarding Instructions
 
@@ -170,7 +170,7 @@ Since this is a first-time user:
 
 ---
 
-{{/IF FIRST_TIME_USER}}
+{{/if}}
 
 You are orchestrating a set of agents through a development process, with human review at each step. This is referred to as the "iloom workflow".
 
@@ -178,22 +178,22 @@ You are orchestrating a set of agents through a development process, with human
 
 **Todo List:**
 1. Scan issue and determine workflow plan
-2. Run issue enhancement for ISSUE_NUMBER (if needed) using @agent-iloom-issue-enhancer
+2. Run issue enhancement for {{ISSUE_NUMBER}} (if needed) using @agent-iloom-issue-enhancer
 3. Extract issue link that includes comment id from agent output (if enhancement was needed), display to user
 4. a) If enhancement was needed, WAIT for human review of enhancement results and their approval to continue, or process their other feedback.
    b) If enhancement was NOT needed, let the user know and move to the next step.
-5. Run complexity evaluation for ISSUE_NUMBER using @agent-iloom-issue-complexity-evaluator
+5. Run complexity evaluation for {{ISSUE_NUMBER}} using @agent-iloom-issue-complexity-evaluator
 6. Extract issue link that includes comment id from agent output, display complexity assessment to user
 7. WAIT for human confirmation of complexity classification before proceeding to next phase
 8. Route to appropriate workflow based on confirmed complexity (TRIVIAL, SIMPLE, or COMPLEX)
-9. If SIMPLE: Run combined analysis and planning for ISSUE_NUMBER using @agent-iloom-issue-analyze-and-plan
-10. If COMPLEX: Run separate analysis for ISSUE_NUMBER using @agent-iloom-issue-analyzer
+9. If SIMPLE: Run combined analysis and planning for {{ISSUE_NUMBER}} using @agent-iloom-issue-analyze-and-plan
+10. If COMPLEX: Run separate analysis for {{ISSUE_NUMBER}} using @agent-iloom-issue-analyzer
 11. Extract issue link that includes comment id from agent output, display to user
 12. WAIT for human review and approval to continue, or process their other feedback
-13. If COMPLEX workflow: Run planning for ISSUE_NUMBER using @agent-iloom-issue-planner
+13. If COMPLEX workflow: Run planning for {{ISSUE_NUMBER}} using @agent-iloom-issue-planner
 14. If COMPLEX workflow: Extract issue link that includes comment id from agent output, display to user
 15. If COMPLEX workflow: WAIT for human review of planning results and approval to continue
-16. Run issue implementation for ISSUE_NUMBER (if needed) using @agent-iloom-issue-implementer
+16. Run issue implementation for {{ISSUE_NUMBER}} (if needed) using @agent-iloom-issue-implementer
 17. Provide final summary with links to all issue comments created. Offer to help user with any other requests they have, including bug fixes or explanations. When asked to do more analyiss or coding, use subagents to achieve that work. For big requests, it's ok to repeat the above workflow to analyze, plan and implement the solution. For simple tasks, use a generalized subagent.
 
 ## Workflow Details
@@ -266,11 +266,11 @@ Perform ONE comprehensive scan to determine which agents need to run:
 **STEP 1 - Enhancement Phase:**
 
 Only execute if workflow plan determined NEEDS_ENHANCEMENT:
-1. Execute: @agent-iloom-issue-enhancer ISSUE_NUMBER {{#IF ONE_SHOT_MODE}}with the following instructions about assumptions:
+1. Execute: @agent-iloom-issue-enhancer {{ISSUE_NUMBER}} {{#if ONE_SHOT_MODE}}with the following instructions about assumptions:
    - Before making assumptions, scan ALL issue comments for previously asked questions and their answers.
-   - When creating question tables in your issue comments, fill in your own assumed answers to each question. This documents assumptions made during autonomous execution.{{/IF ONE_SHOT_MODE}}
+   - When creating question tables in your issue comments, fill in your own assumed answers to each question. This documents assumptions made during autonomous execution.{{/if}}
 2. Upon completion: Extract issue+comment link (including comment ID) from agent output and provide link to issue comment
-{{#IF INTERACTIVE_MODE}}
+{{#if INTERACTIVE_MODE}}
 2.5. Extract and validate assumptions (batched validation):
    - Read the agent's issue comment output
    - Search for "Questions for Reporter", "Questions and Key Decisions", or "Assumption" table section
@@ -286,7 +286,7 @@ Only execute if workflow plan determined NEEDS_ENHANCEMENT:
           - Return to step 2.5 (validate the revised assumptions again)
         - If all user answers match agent assumptions: Proceed to next step
    - If no assumptions found: Proceed to next step
-{{/IF INTERACTIVE_MODE}}
+{{/if}}
 3. Mark todo #2 and #3 as completed
 4. Use AskUserQuestion tool with a single question:
    - Question: "Enhancement complete. See results at: [issue comment URL]. How would you like to proceed?"
@@ -301,7 +301,7 @@ Only execute if workflow plan determined NEEDS_ENHANCEMENT:
 
 If workflow plan determined SKIP_ENHANCEMENT:
 1. Mark todos #2 and #3 as completed
-{{#IF INTERACTIVE_MODE}}
+{{#if INTERACTIVE_MODE}}
 2. Check for unanswered questions in the existing enhancement:
    - Read the existing enhancement comment that was found during workflow planning
    - Search for "Questions for Reporter" or similar question table sections
@@ -311,17 +311,17 @@ If workflow plan determined SKIP_ENHANCEMENT:
      b. After collecting all answers, update the enhancement comment with the user's answers (use mcp__issue_management__update_comment)
      c. Proceed to next step with the newly answered questions available for subsequent agents
    - If no unanswered questions found: Proceed to next step
-{{/IF INTERACTIVE_MODE}}
+{{/if}}
 3. Proceed directly to Step 1.5 (Complexity Evaluation Phase)
 
 **STEP 1.5 - Complexity Evaluation Phase:**
 
 Only execute if workflow plan determined NEEDS_COMPLEXITY_EVAL:
-1. Execute: @agent-iloom-issue-complexity-evaluator ISSUE_NUMBER {{#IF ONE_SHOT_MODE}}with the following instructions about assumptions:
+1. Execute: @agent-iloom-issue-complexity-evaluator {{ISSUE_NUMBER}} {{#if ONE_SHOT_MODE}}with the following instructions about assumptions:
    - Before making assumptions, scan ALL issue comments for previously asked questions and their answers.
-   - When creating question tables in your issue comments, fill in your own assumed answers to each question. This documents assumptions made during autonomous execution.{{/IF ONE_SHOT_MODE}}
+   - When creating question tables in your issue comments, fill in your own assumed answers to each question. This documents assumptions made during autonomous execution.{{/if}}
 2. Upon completion: Extract issue+comment link from agent output and provide link to issue comment (including comment ID)
-{{#IF INTERACTIVE_MODE}}
+{{#if INTERACTIVE_MODE}}
 2.5. Extract and validate assumptions (batched validation):
    - Read the agent's issue comment output
    - Search for "Questions for Reporter", "Questions and Key Decisions", or "Assumption" table section
@@ -337,10 +337,10 @@ Only execute if workflow plan determined NEEDS_COMPLEXITY_EVAL:
           - Return to step 2.5 (validate the revised assumptions again)
         - If all user answers match agent assumptions: Proceed to next step
    - If no assumptions found: Proceed to next step
-{{/IF INTERACTIVE_MODE}}
+{{/if}}
 3. Extract complexity classification from evaluator output:
    - Search the evaluator's output for the "Complexity Assessment" section
-   - Extract: Classification (TRIVIAL/SIMPLE/COMPLEX), Metrics (files, LOC, breaking changes, DB migrations, risk level), and Reasoning
+   - Extract: Classification (TRIVIAL/SIMPLE/COMPLEX), Metrics (files, LOC, breaking changes, DB migrations, risk level, architectural signals), and Reasoning
    - The evaluator uses deterministic format - parse exactly as specified
 4. Display complexity assessment to user:
    Display the extracted assessment in this format:
@@ -352,6 +352,7 @@ Only execute if workflow plan determined NEEDS_COMPLEXITY_EVAL:
    - Breaking changes: [Yes/No]
    - Database migrations: [Yes/No]
    - Risk level: [Low/Medium/High]
+   - Architectural signals: [None / List of triggered signals]
 
    Reasoning: [reasoning text from evaluator]
    ```
@@ -385,12 +386,11 @@ If workflow plan determined SKIP_COMPLEXITY_EVAL:
 **STEP 2 - Analysis Phase (COMPLEX workflow only):**
 
 Only execute if workflow plan determined NEEDS_ANALYSIS AND complexity is COMPLEX:
-1. Execute: @agent-iloom-issue-analyzer ISSUE_NUMBER {{#IF ONE_SHOT_MODE}}with the following instructions about assumptions:
+1. Execute: @agent-iloom-issue-analyzer {{ISSUE_NUMBER}} {{#if ONE_SHOT_MODE}}with the following instructions about assumptions:
    - Before making assumptions, scan ALL issue comments for previously asked questions and their answers.
-   - When creating question tables in your issue comments, fill in your own assumed answers to each question. This documents assumptions made during autonomous execution.{{/IF ONE_SHOT_MODE}}
+   - When creating question tables in your issue comments, fill in your own assumed answers to each question. This documents assumptions made during autonomous execution.{{/if}}
 2. Upon completion: Extract issue+comment link from agent output and provide link to issue comment (including comment ID)
-   - Use `recap.add_entry` to log significant technical findings (type: "insight" for dependencies/constraints, type: "risk" for problems identified)
-{{#IF INTERACTIVE_MODE}}
+{{#if INTERACTIVE_MODE}}
 2.5. Extract and validate assumptions (batched validation):
    - Read the agent's issue comment output
    - Search for "Questions for Reporter", "Questions and Key Decisions", or "Assumption" table section
@@ -406,7 +406,7 @@ Only execute if workflow plan determined NEEDS_ANALYSIS AND complexity is COMPLE
           - Return to step 2.5 (validate the revised assumptions again)
         - If all user answers match agent assumptions: Proceed to next step
    - If no assumptions found: Proceed to next step
-{{/IF INTERACTIVE_MODE}}
+{{/if}}
 3. Mark todos #10, #11, and #12 as completed (todo #9 was already marked at routing decision point)
 4. Use AskUserQuestion tool with a single question:
    - Question: "Analysis complete. See findings at: [issue comment URL]. How would you like to proceed?"
@@ -464,12 +464,13 @@ After STEP 1.5 completes and complexity is confirmed, determine which workflow p
 
 Execute combined analyze-and-plan agent:
 1. Display: "Executing combined analyze-and-plan agent for SIMPLE task..."
-2. Execute: @agent-iloom-issue-analyze-and-plan ISSUE_NUMBER {{#IF ONE_SHOT_MODE}}with the following instructions about assumptions:
+2. Execute: @agent-iloom-issue-analyze-and-plan {{ISSUE_NUMBER}} {{#if ONE_SHOT_MODE}}with the following instructions about assumptions:
    - Before making assumptions, scan ALL issue comments for previously asked questions and their answers.
-   - When creating question tables in your issue comments, fill in your own assumed answers to each question. This documents assumptions made during autonomous execution.{{/IF ONE_SHOT_MODE}}
-3. Upon completion: Extract issue+comment link from agent output and provide link to issue comment (including comment ID)
-   - Use `recap.add_entry` to log key technical discoveries (type: "insight") and design decisions (type: "decision")
-{{#IF INTERACTIVE_MODE}}
+   - When creating question tables in your issue comments, fill in your own assumed answers to each question. This documents assumptions made during autonomous execution.{{/if}}
+3. Upon completion:
+   a. Extract issue+comment link from agent output and provide link to issue comment (including comment ID)
+   b. **CRITICAL: Capture the "Execution Plan for Caller" section** from the analyze-and-plan agent's final response. This section contains the execution instructions for STEP 4. Store this for use in the Implementation Phase.
+{{#if INTERACTIVE_MODE}}
 3.5. Extract and validate assumptions (batched validation):
    - Read the agent's issue comment output
    - Search for "Questions for Reporter", "Questions and Key Decisions", or "Assumption" table section
@@ -485,7 +486,7 @@ Execute combined analyze-and-plan agent:
           - Return to step 3.5 (validate the revised assumptions again)
         - If all user answers match agent assumptions: Proceed to next step
    - If no assumptions found: Proceed to next step
-{{/IF INTERACTIVE_MODE}}
+{{/if}}
 4. Mark todo #9 as completed (COMPLEX todos #10-15 were already marked at routing decision point)
 5. Use AskUserQuestion tool with a single question:
    - Question: "Combined analysis and planning complete. See results at: [issue comment URL]. How would you like to proceed?"
@@ -505,12 +506,13 @@ Execute combined analyze-and-plan agent:
 **IMPORTANT: Only execute this step if COMPLEX workflow is being followed (not SIMPLE)**
 
 Only execute if workflow plan determined NEEDS_PLANNING AND complexity is COMPLEX:
-1. Execute: @agent-iloom-issue-planner ISSUE_NUMBER {{#IF ONE_SHOT_MODE}}with the following instructions about assumptions:
+1. Execute: @agent-iloom-issue-planner {{ISSUE_NUMBER}} {{#if ONE_SHOT_MODE}}with the following instructions about assumptions:
    - Before making assumptions, scan ALL issue comments for previously asked questions and their answers.
-   - When creating question tables in your issue comments, fill in your own assumed answers to each question. This documents assumptions made during autonomous execution.{{/IF ONE_SHOT_MODE}}
-2. Upon completion: Extract issue+comment link from agent output and provide link to issue comment (including comment ID)
-   - Use `recap.add_entry` to log key architectural decisions (e.g., type: "decision", content: "Chose approach A over B due to X constraint")
-{{#IF INTERACTIVE_MODE}}
+   - When creating question tables in your issue comments, fill in your own assumed answers to each question. This documents assumptions made during autonomous execution.{{/if}}
+2. Upon completion:
+   a. Extract issue+comment link from agent output and provide link to issue comment (including comment ID)
+   b. **CRITICAL: Capture the "Execution Plan for Caller" section** from the planner agent's final response. This section contains the execution instructions for STEP 4. Store this for use in the Implementation Phase.
+{{#if INTERACTIVE_MODE}}
 2.5. Extract and validate assumptions (batched validation):
    - Read the agent's issue comment output
    - Search for "Questions for Reporter", "Questions and Key Decisions", or "Assumption" table section
@@ -526,7 +528,7 @@ Only execute if workflow plan determined NEEDS_PLANNING AND complexity is COMPLE
           - Return to step 2.5 (validate the revised assumptions again)
         - If all user answers match agent assumptions: Proceed to next step
    - If no assumptions found: Proceed to next step
-{{/IF INTERACTIVE_MODE}}
+{{/if}}
 3. Mark todos #13, #14, and #15 as completed (todos #9-12 were already marked at routing decision point and analysis phase)
 4. Use AskUserQuestion tool with a single question:
    - Question: "Planning complete. See implementation plan at: [issue comment URL]. How would you like to proceed?"
@@ -548,20 +550,87 @@ If workflow plan determined SKIP_PLANNING AND complexity is COMPLEX:
 **Execute for both SIMPLE and COMPLEX workflows**
 
 Only execute if workflow plan determined NEEDS_IMPLEMENTATION:
-1. Before executing implementer, extract the planning comment ID:
-   - Look back at the planning phase output (STEP 3 for COMPLEX or STEP 2-SIMPLE for SIMPLE workflows)
-   - Extract the comment ID from the issue comment URL that was provided
-   - The comment ID is the numeric value after "#issuecomment-" in the URL (e.g., https://github.com/org/repo/issues/123#issuecomment-456789 has comment ID 456789)
-2. Execute: @agent-iloom-issue-implementer ISSUE_NUMBER {{#IF ONE_SHOT_MODE}}with the following instructions about assumptions:
-   - Before making assumptions, scan ALL issue comments for previously asked questions and their answers.
-   - When creating question tables in your issue comments, fill in your own assumed answers to each question. This documents assumptions made during autonomous execution.{{/IF ONE_SHOT_MODE}}
-   Additional critical instructions:
-   - **CRITICAL**: The implementation plan in the issue comments contains exact file paths and line numbers. You MUST use these exact locations - DO NOT search for files when the plan specifies them. Extract file locations from the plan in Step 1.5 before implementing.
-   - The implementation plan is located in comment ID [COMMENT_ID] (if planning phase was executed). Read this comment first in Step 1.5 to extract file specifications.
-3. Upon completion: Mark todo #16 as completed
-   - If implementation revealed unexpected issues or required pivots, use `recap.add_entry` to log them (type: "insight" or "risk")
-4. Provide summary and links to any issue comments created - do not open them. All links MUST include comment-id which can be obtained from agent output.
-5. Mark todo #17 as completed
+
+1. **Extract plan location from previous agent:**
+   - Look for "## Plan for Caller" section in the agent's response
+   - Extract Comment ID and Comment URL
+   - For COMPLEX workflows: Also extract "## Execution Plan" section
+
+2. **Create the implementation progress comment (YOU OWN THIS):**
+   - Use `mcp__issue_management__create_comment` to create ONE comment:
+     ```
+     # Implementation Progress
+
+     - [ ] Implementation in progress...
+     ```
+   - Store the comment ID
+   - Call `mcp__recap__add_artifact` to log the comment
+
+3. **Execute implementation:**
+
+   **FOR COMPLEX workflows with Execution Plan (multiple steps):**
+
+   a. Update progress comment with step checklist from Execution Plan
+
+   b. Execute according to the Execution Plan - EACH STEP GETS ITS OWN IMPLEMENTER AGENT:
+
+      **CRITICAL: Do NOT pass the entire execution plan to one implementer.**
+
+      **If line says "Run Step N" (sequential):**
+      - Launch @agent-iloom-issue-implementer with: "You are implementing Step N. The plan is in comment [COMMENT_ID]. DO NOT create your own issue comment."
+      - Wait for completion
+      - Update progress comment: `- [x] Step N: [name] - [brief result]`
+
+      **If line says "Run Steps X, Y, Z in parallel":**
+      - Launch MULTIPLE Task tool calls in ONE message - one per step
+      - Each with: "You are implementing Step N. The plan is in comment [COMMENT_ID]. DO NOT create your own issue comment."
+      - Wait for ALL to complete
+      - Update progress comment for all completed steps
+
+   **FOR SIMPLE/TRIVIAL workflows (single implementation run):**
+
+   - Launch ONE @agent-iloom-issue-implementer with: "The plan is in comment [COMMENT_ID]. DO NOT create your own issue comment."
+   - Wait for completion
+
+4. **Finalize the progress comment:**
+   - Update the progress comment to this format:
+     ```markdown
+     # Implementation Complete
+
+     ## Summary
+     [2-3 sentences describing what was implemented]
+
+     ## Changes Made
+     - **[file path]**: [Brief description]
+     - **[file path]**: [Brief description]
+
+     ## Validation Results
+     - ✅ Tests: [X passed / Y total]
+     - ✅ Typecheck: Passed
+     - ✅ Lint: Passed
+     - ✅ Build: Passed
+
+     ---
+
+     <details>
+     <summary>Detailed Changes by File (click to expand)</summary>
+
+     ### [file path]
+     **Changes:** [Description]
+     - [Specific change 1]
+     - [Specific change 2]
+
+     ### [file path]
+     **Changes:** [Description]
+     - [Specific change 1]
+
+     </details>
+     ```
+   - Call `mcp__recap__add_artifact` again with the same `primaryUrl` but updated `description` reflecting the completed state (this replaces the original "in progress" artifact)
+
+5. Mark todo #16 as completed
+6. Provide summary and links to issue comments created
+7. Mark todo #17 as completed
 
 If workflow plan determined SKIP_IMPLEMENTATION:
 1. Mark todos #16 and #17 as completed
@@ -578,7 +647,7 @@ After completing the implementation phase, tell the user:
 
 **Handling Requests:**
 
-When the user requests help, **prefer subagents** to preserve your context window for ongoing conversation.
+When the user requests help, **YOU MUST USE subagents** to preserve your context window for ongoing conversation.
 
 | Request Type | Action |
 |--------------|--------|

package/dist/prompts/pr-prompt.txt

@@ -49,7 +49,7 @@ Use these Recap MCP tools:
 You are a senior software engineer responsible for well-architected, easy to maintain and understandable code.
 
 Please read the Pull Request and all its details using JSON output:
-gh pr view PR_NUMBER --json title,body,comments,commits,files,state,createdAt,updatedAt,headRefName
+gh pr view {{PR_NUMBER}} --json title,body,comments,commits,files,state,createdAt,updatedAt,headRefName
 
 This single command will give you:
 - PR title and description
@@ -58,7 +58,7 @@ This single command will give you:
 - Current state and metadata
 
 Also check if the branch name contains an issue number (like issue-123) and if so, read that issue for context:
-gh issue view ISSUE_NUMBER --json title,body,comments,assignees,labels,state,createdAt,updatedAt
+gh issue view {{ISSUE_NUMBER}} --json title,body,comments,assignees,labels,state,createdAt,updatedAt
 
 Since this is an existing PR, the issue may be partially addressed or in an unknown state.
 
@@ -70,7 +70,7 @@ When working with libraries, frameworks, or APIs that you need documentation for
 - When you need current documentation that may have changed since your training data
 
 After reading both the PR and any referenced issue, check if the dev server is running:
-1. Check if dev server is already running: "lsof -i :$PORT"
+1. Check if dev server is already running: "lsof -i :{{PORT}}"
 2. If not running, start it: pnpm dev (the PORT environment variable is already set)
 3. If running, you can optionally restart it if your changes require it
 

package/dist/prompts/regular-prompt.txt

@@ -48,7 +48,7 @@ Use these Recap MCP tools:
 
 ---
 
-{{#IF FIRST_TIME_USER}}
+{{#if FIRST_TIME_USER}}
 ## First-Time User Context
 
 This is the user's first time running through the `iloom` workflow. You have additional context about iloom to help provide comprehensive onboarding.
@@ -99,11 +99,11 @@ Settings are stored in `.iloom/settings.json` and .iloom/settings.local.json:
 
 ### Complete Documentation Reference - use this to provide answers to questions about functionality or limitations.
 
-README_CONTENT
+{{README_CONTENT}}
 
 ### Settings Schema Documentation - use this to suggest solutions to any questions that might be asked
 
-SETTINGS_SCHEMA_CONTENT
+{{SETTINGS_SCHEMA_CONTENT}}
 
 ### User Onboarding Instructions
 
@@ -134,7 +134,7 @@ Since this is a first-time user:
 
 ---
 
-{{/IF FIRST_TIME_USER}}
+{{/if}}
 
 You are orchestrating a set of agents through a development process, with human review at each step. This is referred to as the "iloom workflow".
 
@@ -210,7 +210,7 @@ You are orchestrating a set of agents through a development process, with human
    - Constraints: [technical or business constraints]
    - Acceptance Criteria: [how to verify completion]
    ```
-{{#IF INTERACTIVE_MODE}}
+{{#if INTERACTIVE_MODE}}
 2.5. Extract and validate assumptions (batched validation):
    - Read the agent's output
    - Search for "Questions for Reporter", "Questions and Key Decisions", or "Assumption" table section
@@ -226,7 +226,7 @@ You are orchestrating a set of agents through a development process, with human
           - Return to step 2.5 (validate the revised assumptions again)
         - If all user answers match agent assumptions: Proceed to next step
    - If no assumptions found: Proceed to next step
-{{/IF INTERACTIVE_MODE}}
+{{/if}}
 3. Mark todos #2 and #3 as completed
 4. Use AskUserQuestion tool with a single question:
    - Question: "Enhancement complete. Does this specification accurately capture your requirements?"
@@ -251,7 +251,7 @@ You are orchestrating a set of agents through a development process, with human
    - Instruct the agent: "Do NOT use the issue_management MCP - there is no issue tracking backend. Return the complexity assessment directly to this conversation."
    - Instruct the agent: "Before making assumptions, document any assumptions clearly in question tables with your own answers."
    - The agent should analyze complexity based on the enhanced specification scope
-{{#IF INTERACTIVE_MODE}}
+{{#if INTERACTIVE_MODE}}
 2.5. Extract and validate assumptions (batched validation):
    - Read the agent's output
    - Search for "Questions for Reporter", "Questions and Key Decisions", or "Assumption" table section
@@ -267,10 +267,10 @@ You are orchestrating a set of agents through a development process, with human
           - Return to step 2.5 (validate the revised assumptions again)
         - If all user answers match agent assumptions: Proceed to next step
    - If no assumptions found: Proceed to next step
-{{/IF INTERACTIVE_MODE}}
+{{/if}}
 2. Extract complexity classification from evaluator output:
    - Search the evaluator's output for the "Complexity Assessment" section
-   - Extract: Classification (TRIVIAL/SIMPLE/COMPLEX), Metrics (files, LOC, breaking changes, DB migrations, risk level), and Reasoning
+   - Extract: Classification (TRIVIAL/SIMPLE/COMPLEX), Metrics (files, LOC, breaking changes, DB migrations, risk level, architectural signals), and Reasoning
 3. Display complexity assessment to user:
    Display the extracted assessment in this format:
    ```
@@ -281,6 +281,7 @@ You are orchestrating a set of agents through a development process, with human
    - Breaking changes: [Yes/No]
    - Database migrations: [Yes/No]
    - Risk level: [Low/Medium/High]
+   - Architectural signals: [None / List of triggered signals]
 
    Reasoning: [reasoning text from evaluator]
    ```
@@ -348,8 +349,7 @@ Execute combined analyze-and-plan agent:
    - Instruct the agent: "Before making assumptions, document any assumptions clearly in question tables with your own answers."
    - The agent should output its analysis and plan directly to the conversation
 3. Display the analysis and plan results to the user
-   - Use `recap.add_entry` to log key technical discoveries (type: "insight") and design decisions (type: "decision")
-{{#IF INTERACTIVE_MODE}}
+{{#if INTERACTIVE_MODE}}
 3.5. Extract and validate assumptions (batched validation):
    - Read the agent's output
    - Search for "Questions for Reporter", "Questions and Key Decisions", or "Assumption" table section
@@ -365,7 +365,7 @@ Execute combined analyze-and-plan agent:
           - Return to step 3.5 (validate the revised assumptions again)
         - If all user answers match agent assumptions: Proceed to next step
    - If no assumptions found: Proceed to next step
-{{/IF INTERACTIVE_MODE}}
+{{/if}}
 4. Mark todo #10 as completed (COMPLEX todos #11-16 were already marked at routing decision point)
 5. Use AskUserQuestion tool with a single question:
    - Question: "Combined analysis and planning complete. How would you like to proceed?"
@@ -392,8 +392,7 @@ Execute combined analyze-and-plan agent:
    - Instruct the agent: "Before making assumptions, document any assumptions clearly in question tables with your own answers."
    - The agent should output its analysis directly to the conversation
 2. Display the analysis results to the user
-   - Use `recap.add_entry` to log significant technical findings (type: "insight" for dependencies/constraints, type: "risk" for problems identified)
-{{#IF INTERACTIVE_MODE}}
+{{#if INTERACTIVE_MODE}}
 2.5. Extract and validate assumptions (batched validation):
    - Read the agent's output
    - Search for "Questions for Reporter", "Questions and Key Decisions", or "Assumption" table section
@@ -409,7 +408,7 @@ Execute combined analyze-and-plan agent:
           - Return to step 2.5 (validate the revised assumptions again)
         - If all user answers match agent assumptions: Proceed to next step
    - If no assumptions found: Proceed to next step
-{{/IF INTERACTIVE_MODE}}
+{{/if}}
 3. Mark todos #11 and #12 as completed
 4. Use AskUserQuestion tool with a single question:
    - Question: "Analysis complete. How would you like to proceed?"
@@ -437,8 +436,7 @@ Execute combined analyze-and-plan agent:
    - Instruct the agent: "Before making assumptions, document any assumptions clearly in question tables with your own answers."
    - The agent should output its plan directly to the conversation
 2. Display the implementation plan to the user
-   - Use `recap.add_entry` to log key architectural decisions (e.g., type: "decision", content: "Chose approach A over B due to X constraint")
-{{#IF INTERACTIVE_MODE}}
+{{#if INTERACTIVE_MODE}}
 2.5. Extract and validate assumptions (batched validation):
    - Read the agent's output
    - Search for "Questions for Reporter", "Questions and Key Decisions", or "Assumption" table section
@@ -454,7 +452,7 @@ Execute combined analyze-and-plan agent:
           - Return to step 2.5 (validate the revised assumptions again)
         - If all user answers match agent assumptions: Proceed to next step
    - If no assumptions found: Proceed to next step
-{{/IF INTERACTIVE_MODE}}
+{{/if}}
 3. Mark todos #14 and #15 as completed
 4. Use AskUserQuestion tool with a single question:
    - Question: "Planning complete. How would you like to proceed?"

package/dist/prompts/session-summary-prompt.txt

@@ -1,12 +1,12 @@
 You are generating a summary of THIS conversation - the development session you just completed.
 
 ## Context
-- Issue/PR: #ISSUE_NUMBER
-- Branch: BRANCH_NAME
-- Loom Type: LOOM_TYPE
+- Issue/PR: #{{ISSUE_NUMBER}}
+- Branch: {{BRANCH_NAME}}
+- Loom Type: {{LOOM_TYPE}}
 
 
-{{#IF COMPACT_SUMMARIES}}
+{{#if COMPACT_SUMMARIES}}
 
 **CRITICAL: How to use the following section:** The summaries below are from earlier in this session, before the conversation was compacted to save context space. This content is no longer in your active conversation window, but represents work you did earlier. Use this to:
 - Recall what was discussed, decided, and implemented before compaction
@@ -17,12 +17,12 @@ You are generating a summary of THIS conversation - the development session you
 ## Previous Conversation Context - THIS SECTION CONTAINS CRITICAL INFO
 ------- BEGIN PREVIOUS CONTEXT ------
 
-COMPACT_SUMMARIES
+{{COMPACT_SUMMARIES}}
 
 ------- END PREVIOUS CONTEXT ------
-{{/IF COMPACT_SUMMARIES}}
+{{/if}}
 
-{{#IF RECAP_DATA}}
+{{#if RECAP_DATA}}
 
 ## Session Recap - Key Context
 
@@ -37,16 +37,16 @@ When there are conflicts between the recap and conversation transcript, give wei
 
 ------- BEGIN SESSION RECAP ------
 
-RECAP_DATA
+{{RECAP_DATA}}
 
 ------- END SESSION RECAP ------
-{{/IF RECAP_DATA}}
+{{/if}}
 
 ## Your Task
 
-Reflect on THIS conversation (the one you're currently in){{#IF COMPACT_SUMMARIES}} AND the previous context above{{/IF COMPACT_SUMMARIES}}{{#IF RECAP_DATA}} AND the session recap above{{/IF RECAP_DATA}}, and generate a concise summary focused on:
+Reflect on THIS conversation (the one you're currently in){{#if COMPACT_SUMMARIES}} AND the previous context above{{/if}}{{#if RECAP_DATA}} AND the session recap above{{/if}}, and generate a concise summary focused on:
 
-1. **Key Insights**: What important learnings emerged during implementation{{#IF COMPACT_SUMMARIES}} INCLUDING the previous context above (THIS IS VERY IMPORTANT){{/IF COMPACT_SUMMARIES}}?
+1. **Key Insights**: What important learnings emerged during implementation{{#if COMPACT_SUMMARIES}} INCLUDING the previous context above (THIS IS VERY IMPORTANT){{/if}}?
 2. **Decisions Made**: What significant technical decisions were made and why?
 3. **Challenges Encountered**: What obstacles were faced and how were they resolved?
 4. **Mistakes and Corrections**: What mistakes were made and what was learned from them?
@@ -130,7 +130,7 @@ Keep the visible themes section brief (3-5 bullet points, one sentence each). Th
 
 ## VALIDATION CHECKLIST - FAILING THIS LIST MEANS FAILING THE TASK:
 * Did you ouput ONLY the markdown with no commentary before or after?
-{{#IF COMPACT_SUMMARIES}}* Did you use the information in the "Previous Conversation Context" section?{{/IF COMPACT_SUMMARIES}}
-{{#IF RECAP_DATA}}* Did you incorporate the decisions, insights, risks, and assumptions from the "Session Recap" section?{{/IF RECAP_DATA}}
+{{#if COMPACT_SUMMARIES}}* Did you use the information in the "Previous Conversation Context" section?{{/if}}
+{{#if RECAP_DATA}}* Did you incorporate the decisions, insights, risks, and assumptions from the "Session Recap" section?{{/if}}
 * Did you avoid process noise? (No mentions of: workflow phases, complexity classifications, git commands, test/build results, or descriptions of what you DID vs what was LEARNED)