@codeyam/codeyam-cli 0.1.0-staging.036391e → 0.1.0-staging.03e0fb2

package/codeyam-cli/templates/{codeyam:memory.md → codeyam-memory.md}

@@ -1,5 +1,5 @@
 ---
-name: codeyam:memory
+name: codeyam-memory
 autoApprove: true
 description: |
   Generate and maintain Claude Rules for your codebase based on thorough analysis.
@@ -13,19 +13,14 @@ This skill helps you generate and maintain Claude Rules (`.claude/rules/`) that
 
 ## Core Principle: Document Confusion, Not Information
 
-**Good rules** explain things that are NOT obvious from reading the code:
+**Valuable rules** capture knowledge that reading the code alone wouldn't reveal:
 
 - Historical context (why code evolved this way)
 - Hidden relationships (files that must change together)
 - Gotchas that caused bugs
 - Non-obvious conventions
 
-**Bad rules** document things Claude can easily ascertain:
-
-- What functions do (Claude can read the code)
-- Type definitions (Claude can see them)
-- Directory structure (Claude can explore it)
-- Basic patterns (Claude knows common patterns)
+Skip documenting things Claude can determine by reading code: function signatures, type definitions, directory structure, and common patterns.
 
 ## When to Use This Skill
 
@@ -41,7 +36,9 @@ Check if this is the first time running memory.
 
 ### 1A. Add Documentation Section to CLAUDE.md
 
-If CLAUDE.md doesn't contain a "When Confused / With Mistakes" section, add close to the top:
+If CLAUDE.md already contains a "Documenting Confusion / Mistakes" section, skip this step entirely.
+
+Otherwise, add **only** the section below — do not modify or add any other content to CLAUDE.md. If CLAUDE.md doesn't exist, create it with just a `# Project` heading followed by this section:
 
 ```markdown
 ## Continuous Documentation
@@ -61,6 +58,8 @@ It is very important to document any tribal knowledge, complex architectural dec
 Please see `.codeyam/rules/instructions.md` for guidance.
 ```
 
+**Important:** Do not add project descriptions, architecture summaries, or any other content to CLAUDE.md. Only add the exact section above.
+
 ### 1B. Verify Instructions File
 
 Check that `.codeyam/rules/instructions.md` exists (it should be created during `codeyam init`). If missing, copy it from `codeyam-cli/templates/rules-instructions.md`.
@@ -275,7 +274,7 @@ Before generating each rule, verify it passes these tests:
 
 **2. Code-derivable check**: Read the files the rule will cover. Could the rule's content be determined by reading those files alone?
 
-- If YES → rule probably not needed (Claude can read the code)
+- If YES → the code is its own documentation — prefer keeping rules for non-derivable insights
 - If NO (historical context, edge cases, non-obvious behavior) → rule is valuable
 
 **3. Prevention check**: Would this rule have prevented one of the confusion commits you found?
@@ -301,7 +300,7 @@ This caused a bug where `entity` matched `entityCode` (siblings, not parent-chil
 - Not code-derivable: Code doesn't explain why boundary checking matters
 - Prevention: Would prevent future prefix-matching bugs
 
-**❌ Bad rule** (fails tests):
+**Compare with a weaker alternative** (fails the checks):
 
 ```markdown
 ## Running Tests
@@ -309,9 +308,7 @@ This caused a bug where `entity` matched `entityCode` (siblings, not parent-chil
 Use `pnpm jest` to run tests. Configuration is in `jest.config.ts`.
 ```
 
-- No confusion evidence (no commits showing people struggled with this)
-- Code-derivable: Anyone can see `jest.config.ts` exists
-- Doesn't prevent any confusion
+- No confusion evidence, code-derivable, and wouldn't prevent future mistakes
 
 ### 5B. Rule File Guidelines
 
@@ -319,17 +316,13 @@ Use `pnpm jest` to run tests. Configuration is in `jest.config.ts`.
    - Rule for `src/api/` → `.claude/rules/src/api/architecture.md`
    - Rule for testing patterns → `.claude/rules/testing-patterns.md`
 
-2. **Paths must be specific**
-   - Good: `paths: ['src/api/**/*.ts']`
-   - Bad: `paths: ['**/*.ts']` (too broad, wastes context)
+2. **Paths must be specific** — use `paths: ['src/api/**/*.ts']` rather than `'**/*.ts'` (too broad wastes context)
 
 3. **Content should explain "why" not just "what"**
    - Focus on the reasoning, history, or gotcha
    - Be concise - every word costs context
 
-4. **Timestamp must be current**
-   - Use ISO 8601 format: `2026-01-27T15:30:00Z`
-   - This enables the pre-commit hook enforcement
+4. **Audit dates live in `.claude/codeyam-rule-state.json`** (managed by `codeyam memory touch`). Keep rule frontmatter limited to `paths`.
 
 ### Rule Template
 
@@ -337,7 +330,6 @@ Use `pnpm jest` to run tests. Configuration is in `jest.config.ts`.
 ---
 paths:
   - 'specific/path/**/*.ts'
-timestamp: [CURRENT_ISO_TIMESTAMP]
 ---
 
 ## [Clear, Descriptive Title]
@@ -374,7 +366,7 @@ After generating rules based on your analysis and user answers:
 5. **Remind the user** to commit the new rules:
    ```
    git add .claude/rules/ .codeyam/rules/
-   git commit -m "Add rules for Claude Code (generated via /codeyam:memory)"
+   git commit -m "Add rules for Claude Code (generated via /codeyam-memory)"
    ```
 
 ---
@@ -394,11 +386,11 @@ After generating rules based on your analysis and user answers:
 The pre-commit hook **blocks commits** when:
 
 - Code files matching a rule's `paths` are modified
-- The rule's `timestamp` is older than the code changes
+- The rule's `lastAuditedAt` in `.claude/codeyam-rule-state.json` is older than the code changes
 
 To proceed:
 
 1. Review the flagged rule(s)
 2. Update content if needed
-3. Update the `timestamp` to current time
+3. Run `codeyam memory touch` to mark rules as audited in `.claude/codeyam-rule-state.json`
 4. Stage and commit

package/codeyam-cli/templates/{codeyam:new-rule.md → codeyam-new-rule.md}

@@ -1,5 +1,5 @@
 ---
-name: codeyam:new-rule
+name: codeyam-new-rule
 autoApprove: true
 description: |
   Create a new Claude Rule for documenting codebase patterns.
@@ -9,5 +9,3 @@ description: |
 # Create New Claude Rule
 
 Read `.codeyam/rules/instructions.md` for detailed guidance on structure and formatting.
-
-If the instructions file doesn't exist, copy it from `codeyam-cli/templates/rules-instructions.md`.

package/codeyam-cli/templates/{codeyam:setup.md → codeyam-setup.md}

@@ -1,5 +1,5 @@
 ---
-name: codeyam:setup
+name: codeyam-setup
 autoApprove: true
 description: |
   Use this skill when the user asks to "setup CodeYam" or needs to configure CodeYam for their project.
@@ -52,6 +52,18 @@ codeyam validate-mock .codeyam/universal-mocks/{path-to-your-mock}
 
 ## Setup Workflow
 
+### Step 0: Ensure Simulation Infrastructure
+
+Before configuring the dev server or mocks, ensure the simulation infrastructure is installed.
+
+```bash
+codeyam setup-simulations
+```
+
+This is **idempotent** — if already set up, each step is detected and skipped. On first run it installs analyzer dependencies, Playwright chromium, and creates baseline entities (several minutes). Subsequent runs complete in seconds.
+
+If it fails with "No web applications found", the project doesn't support simulations — inform the user and stop.
+
 ### Step 1: Configure Webapp Start Command
 
 **ACTION 1:** Read configuration files:

package/codeyam-cli/templates/{codeyam:sim.md → codeyam-sim.md}

@@ -1,5 +1,5 @@
 ---
-name: codeyam:sim
+name: codeyam-sim
 autoApprove: true
 description: |
   Use this skill to create interactive simulations of components and functions using CodeYam's analysis.

package/codeyam-cli/templates/{codeyam:test.md → codeyam-test.md}

@@ -1,5 +1,5 @@
 ---
-name: codeyam:test
+name: codeyam-test
 autoApprove: true
 description: |
   Use this skill to write comprehensive unit and integration tests using CodeYam's mock generation.

package/codeyam-cli/templates/{codeyam:verify.md → codeyam-verify.md}

@@ -1,5 +1,5 @@
 ---
-name: codeyam:verify
+name: codeyam-verify
 autoApprove: true
 description: |
   Use this skill after making code changes that impact application functionality.

package/codeyam-cli/templates/hooks/staleness-check.sh

@@ -0,0 +1,43 @@
+#!/bin/bash
+# Staleness check hook - runs after file edits to check if related rules need review
+# Receives JSON input via stdin with tool info
+
+set -e
+
+# Read the input JSON
+INPUT=$(cat)
+
+# Extract the file path that was edited
+FILE_PATH=$(echo "$INPUT" | jq -r '.tool_input.file_path // .tool_input.path // empty' 2>/dev/null)
+
+if [ -z "$FILE_PATH" ]; then
+  exit 0  # No file path, nothing to check
+fi
+
+# Find rules that match this file path
+RULES_DIR="${CLAUDE_PROJECT_DIR}/.claude/rules"
+
+if [ ! -d "$RULES_DIR" ]; then
+  exit 0  # No rules directory
+fi
+
+# Search for rules whose paths might match the edited file
+MATCHING_RULES=""
+while IFS= read -r -d '' rule_file; do
+  # Extract paths from frontmatter
+  PATHS=$(sed -n '/^---$/,/^---$/p' "$rule_file" | grep -E "^\s*-\s*'" | sed "s/.*'\(.*\)'.*/\1/")
+
+  for pattern in $PATHS; do
+    # Simple check if the file might match the pattern
+    if [[ "$FILE_PATH" == *"${pattern%%\**}"* ]]; then
+      MATCHING_RULES="$MATCHING_RULES\n- $(basename "$rule_file")"
+      break
+    fi
+  done
+done < <(find "$RULES_DIR" -name "*.md" -print0 2>/dev/null)
+
+if [ -n "$MATCHING_RULES" ]; then
+  echo "📋 Modified file may have related rules that need review:$MATCHING_RULES"
+fi
+
+exit 0

package/codeyam-cli/templates/prompts/conversation-guidance.txt

@@ -0,0 +1,44 @@
+### What to look for
+
+Read the full transcript for these signals:
+
+**User corrections or redirections**
+- "no", "actually", "that's not right", "you need to also...", "you missed..."
+- User provides information Claude didn't know or couldn't infer from code
+- User reminds Claude of a step, pattern, or relationship
+- A correction about something other than current task requirements is ALWAYS rule-worthy
+
+**Investigation and debugging**
+- Claude tried multiple approaches, read logs, or tested hypotheses
+- Investigation revealed non-obvious behavior or root causes
+- Debugging strategies that worked (or didn't) for specific areas
+
+**Architecture not evident in code**
+- Files that must change together (templates + installation, routes + registration)
+- Complex files, data flows, pipelines, or system interactions that would benefit from an overview
+
+**Commands and workflows**
+- Specific commands or flags needed for this area
+- Order of operations that matters ("must run X before Y")
+
+**Ignore:**
+- Corrections to requirements for the current feature or bug
+- Confusion isolated to the current work session (won't recur)
+
+### Before creating a rule
+
+**Critical check:** Read the actual source files that were modified. If the code already contains comments, guard patterns, or tests that explain the insight, the code is the documentation — skip the rule unless the file is complex and you've made a mistake or the user had to interrupt and correct you.
+
+Show your thinking before proceeding with creating or updating rules.
+
+### How to write rules
+
+**Rules must be forward-looking, not historical.** You are reading a session transcript where bugs were found and fixed, but the rule should describe the *current* codebase, not tell the story of what went wrong, what was fixed, etc. The code has already been updated — past bugs are no longer relevant.
+
+- **DO**: State constraints and requirements ("this script MUST copy directories recursively, not just files")
+- **DO**: Explain *why* something matters ("errors in prompt copying are silently caught, so missing directories won't surface as errors")
+- **DON'T**: Describe what old code did ("the old version only copied files, causing X to be missing")
+- **DON'T**: Narrate the debugging journey ("we discovered that the catch block was swallowing errors")
+- **DON'T**: Note issues or known gaps if they are actively being worked on!
+
+Think of the reader as a developer about to modify these files. They need to know what constraints to preserve and what pitfalls to watch for — not what happened in the past if it is no longer relevant.

package/codeyam-cli/templates/prompts/conversation-prompt.txt

@@ -0,0 +1,28 @@
+FIRST: Read `.codeyam/rules/instructions.md` — it contains the required format, rule placement via the rule-path API, and an example rule. You MUST follow this format exactly when creating or editing rules.
+
+THEN: Read the file {{CONTEXT_FILE}} and follow the instructions inside.
+
+Analyze the conversation transcript for rule-worthy learnings:
+- User corrections, redirections, or information Claude didn't know
+- Investigation results and debugging knowledge
+- Architecture and relationships not obvious from code
+- Commands, workflows, and processes
+
+Access and read files in the repo or in the .claude folder as needed.
+
+Create new rules only when the learnings meet the guidelines in the context file.
+
+IMPORTANT: If you create ANY rule files, write a short summary to `{{NOTIFICATION_FILE}}`. The summary should list each rule change, e.g.:
+```
+The background rule-reflection agent created the following rules:
+- Created `.claude/rules/tooling/new-pattern.md` — documents X pattern
+```
+Only write the notification file when rules are created.
+
+The project root is {{PROJECT_DIR}}
+
+CRITICAL: All rule files MUST be written to {{PROJECT_DIR}}/.claude/rules/ (the project directory). Always use the full absolute path when writing rule files.
+
+CRITICAL: Before writing any rule file, you MUST run the rule-path command to determine the correct subdirectory:
+  codeyam memory rule-path path/one path/two
+Pass all paths from your frontmatter. The command returns the correct .claude/rules/ subdirectory as JSON. Do NOT guess the placement from the first path — rules with paths spanning multiple directories belong at their common ancestor.

package/codeyam-cli/templates/prompts/interruption-prompt.txt

@@ -0,0 +1,31 @@
+FIRST: Read `.codeyam/rules/instructions.md` — it contains the required format, rule placement via the rule-path API, and an example rule. You MUST follow this format exactly when creating or editing rules.
+
+THEN: Read the file {{CONTEXT_FILE}} and follow the instructions inside.
+
+The user interrupted Claude mid-response — a strong signal of confusion or misunderstanding.
+Analyze both Claude's interrupted output and the user's follow-up to determine what went wrong.
+
+Look for:
+- Claude heading in a wrong direction that the user had to correct
+- Misunderstanding of project conventions, architecture, or dependencies
+- Missing context that caused Claude to make incorrect assumptions
+- Patterns that would recur in future sessions without a rule
+
+Access and read files in the repo or in the .claude folder as needed.
+
+Create new rules only when the learnings meet the guidelines in the context file.
+
+IMPORTANT: If you create ANY rule files, write a short summary to `{{NOTIFICATION_FILE}}`. The summary should list each rule change, e.g.:
+```
+The background rule-reflection agent created the following rules:
+- Created `.claude/rules/tooling/new-pattern.md` — documents X pattern
+```
+Only write the notification file when rules are created.
+
+The project root is {{PROJECT_DIR}}
+
+CRITICAL: All rule files MUST be written to {{PROJECT_DIR}}/.claude/rules/ (the project directory). Always use the full absolute path when writing rule files.
+
+CRITICAL: Before writing any rule file, you MUST run the rule-path command to determine the correct subdirectory:
+  codeyam memory rule-path path/one path/two
+Pass all paths from your frontmatter. The command returns the correct .claude/rules/ subdirectory as JSON. Do NOT guess the placement from the first path — rules with paths spanning multiple directories belong at their common ancestor.

package/codeyam-cli/templates/prompts/stale-rules-prompt.txt

@@ -0,0 +1,24 @@
+FIRST: Read `.codeyam/rules/instructions.md` — it contains the required format, rule placement via the rule-path API, and an example rule. You MUST follow this format exactly when creating or editing rules.
+
+THEN: Read the file {{CONTEXT_FILE}} and follow the instructions inside.
+
+For each stale rule:
+1. Review the inline rule content and the diff to determine if the rule needs updating
+2. If it needs updating, edit the rule file in .claude/rules/ — also trim prose and unnecessary headers (most rules should be a few bullets)
+3. Run `codeyam memory touch <rule-path1> <rule-path2> ...` with the SPECIFIC rule paths you reviewed to mark them as audited in .claude/codeyam-rule-state.json
+   Example: `codeyam memory touch tooling/cli-build.md packages/ai/execution-flow-prioritization.md`
+
+Write a summary to `{{NOTIFICATION_FILE}}` listing each action taken, even if you only ran `codeyam memory touch` without content changes. Example:
+```
+The background rule-reflection agent updated the following rules:
+- Reviewed `.claude/rules/example.md` — no content changes, ran `codeyam memory touch`
+- Created `.claude/rules/tooling/new-pattern.md` — documents X pattern
+```
+
+The project root is {{PROJECT_DIR}}
+
+CRITICAL: All rule files MUST be written to {{PROJECT_DIR}}/.claude/rules/ (the project directory), NOT ~/.claude/rules/ (the user home directory). Always use the full absolute path when writing rule files.
+
+CRITICAL: Before writing any rule file, you MUST run the rule-path command to determine the correct subdirectory:
+  codeyam memory rule-path path/one path/two
+Pass all paths from your frontmatter. The command returns the correct .claude/rules/ subdirectory as JSON. Do NOT guess the placement from the first path — rules with paths spanning multiple directories belong at their common ancestor.

package/codeyam-cli/templates/rule-notification-hook.py

@@ -14,6 +14,7 @@ Supports four notification files (legacy combined + split agents):
 - rule-notification-interruption.md (interruption review agent)
 """
 
+import json
 import os
 import sys
 
@@ -26,27 +27,53 @@ NOTIFICATION_FILES = [
 ]
 
 
+def get_project_slug():
+    """
+    Derive project slug from .codeyam/config.json (matching getProjectSlug() on the TS side).
+    Falls back to os.path.basename(project_dir) if config is absent or malformed.
+    """
+    project_dir = os.environ.get('CLAUDE_PROJECT_DIR', os.getcwd())
+    try:
+        config_path = os.path.join(project_dir, '.codeyam', 'config.json')
+        with open(config_path, 'r') as f:
+            config = json.load(f)
+        slug = config.get('projectSlug', '')
+        if slug:
+            return slug
+    except (IOError, json.JSONDecodeError, KeyError):
+        pass
+    return os.path.basename(project_dir)
+
+
 def main():
     collected = []
+    slug = get_project_slug()
+
+    # Check slug subdirectory first, then fall back to flat directory
+    dirs_to_check = [os.path.join(MARKER_DIR, slug), MARKER_DIR]
 
     for filename in NOTIFICATION_FILES:
-        filepath = os.path.join(MARKER_DIR, filename)
-        if not os.path.exists(filepath):
-            continue
-
-        try:
-            with open(filepath, 'r') as f:
-                content = f.read().strip()
-        except IOError:
-            continue
-
-        if content:
-            collected.append(content)
-
-        try:
-            os.remove(filepath)
-        except OSError:
-            pass
+        for check_dir in dirs_to_check:
+            filepath = os.path.join(check_dir, filename)
+            if not os.path.exists(filepath):
+                continue
+
+            try:
+                with open(filepath, 'r') as f:
+                    content = f.read().strip()
+            except IOError:
+                continue
+
+            if content:
+                collected.append(content)
+
+            try:
+                os.remove(filepath)
+            except OSError:
+                pass
+
+            # Found in this directory — don't check the fallback
+            break
 
     if collected:
         print('\n\n'.join(collected))

package/codeyam-cli/templates/rule-reflection-hook.py

@@ -120,6 +120,51 @@ def read_rule_content(rule_name):
     return text
 
 
+def get_project_slug():
+    """
+    Derive project slug from .codeyam/config.json (matching getProjectSlug() on the TS side).
+    Falls back to os.path.basename(project_dir) if config is absent or malformed.
+    """
+    project_dir = os.environ.get('CLAUDE_PROJECT_DIR', os.getcwd())
+    try:
+        config_path = os.path.join(project_dir, '.codeyam', 'config.json')
+        with open(config_path, 'r') as f:
+            config = json.load(f)
+        slug = config.get('projectSlug', '')
+        if slug:
+            return slug
+    except (IOError, json.JSONDecodeError, KeyError):
+        pass
+    return os.path.basename(project_dir)
+
+
+def load_memory_settings():
+    """
+    Load memory settings from .codeyam/config.json.
+    Returns dict with safe defaults when absent or malformed.
+    """
+    defaults = {
+        'conversationReflection': True,
+        'ruleMaintenance': True,
+        'promptModel': 'haiku',
+    }
+    try:
+        project_dir = os.environ.get('CLAUDE_PROJECT_DIR', os.getcwd())
+        config_path = os.path.join(project_dir, '.codeyam', 'config.json')
+        with open(config_path, 'r') as f:
+            config = json.load(f)
+        memory = config.get('memory', {})
+        if not isinstance(memory, dict):
+            return defaults
+        return {
+            'conversationReflection': memory.get('conversationReflection', True),
+            'ruleMaintenance': memory.get('ruleMaintenance', True),
+            'promptModel': memory.get('promptModel', 'haiku'),
+        }
+    except (IOError, json.JSONDecodeError, KeyError):
+        return defaults
+
+
 def get_stale_rules():
     """
     Run `codeyam memory status` and parse the output to find stale rules.
@@ -157,8 +202,8 @@ def get_stale_rules():
                 # Look for the next few lines for details
                 for j in range(i + 1, min(i + 4, len(lines))):
                     detail = lines[j].strip()
-                    if detail.startswith('Rule timestamp:'):
-                        rule_info['rule_timestamp'] = detail.replace('Rule timestamp:', '').strip()
+                    if detail.startswith('Last audited:'):
+                        rule_info['last_audited'] = detail.replace('Last audited:', '').strip()
                     elif detail.startswith('Newest file:'):
                         rule_info['newest_file'] = detail.replace('Newest file:', '').strip()
                     elif detail.startswith('File modified:'):
@@ -286,7 +331,7 @@ def build_stale_rules_context(stale_rules):
     parts.append("For each rule, review the rule content and the diff of changes, then:")
     parts.append("1. Determine if the rule content needs updating based on the code changes")
     parts.append("2. Update the rule if needed")
-    parts.append("3. ALWAYS update the timestamp (run `codeyam memory touch`)\n")
+    parts.append("3. Run `codeyam memory touch <rule-path1> <rule-path2> ...` with the SPECIFIC rule paths you reviewed to mark them as audited\n")
 
     for rule in stale_rules:
         parts.append(f"### {rule['name']}")
@@ -298,8 +343,8 @@ def build_stale_rules_context(stale_rules):
             parts.append(f"  Changed file: {rule['newest_file']}")
         if rule.get('file_modified'):
             parts.append(f"  File modified: {rule['file_modified']}")
-        if rule.get('rule_timestamp'):
-            parts.append(f"  Rule timestamp: {rule['rule_timestamp']}")
+        if rule.get('last_audited'):
+            parts.append(f"  Last audited: {rule['last_audited']}")
         if rule.get('diff'):
             parts.append(f"  Changes:")
             for line in rule['diff'].split('\n'):
@@ -373,7 +418,7 @@ def build_interruption_context(conversation_snippets, follow_up_prompt, modified
     return '\n'.join(parts)
 
 
-def spawn_claude_agent(prompt, log_file, project_dir):
+def spawn_claude_agent(prompt, log_file, project_dir, model='haiku'):
     """Spawn a detached claude -p agent as a background process."""
     try:
         log_fh = open(log_file, 'w')
@@ -381,7 +426,8 @@ def spawn_claude_agent(prompt, log_file, project_dir):
         env['CODEYAM_RULE_AGENT'] = '1'
         subprocess.Popen(
             ['claude', '-p', prompt,
-             '--model', 'haiku',
+             '--model', model,
+             '--no-session-persistence',
              '--output-format', 'stream-json', '--verbose',
              '--allowedTools', 'Read,Edit,Write,Bash,Glob,Grep'],
             cwd=project_dir,
@@ -427,14 +473,17 @@ def handle_stop(hook_input):
     agent spawn) runs first. The slow `get_stale_rules()` call (~10s) runs last
     so the hook timeout doesn't kill us before the critical work is done.
     """
+    settings = load_memory_settings()
+
     session_id = hook_input.get('session_id', '')
     transcript_path = hook_input.get('transcript_path', '')
 
     if not session_id or not transcript_path:
         return
 
-    marker_dir = Path('/tmp/claude-rule-markers')
-    marker_dir.mkdir(exist_ok=True)
+    slug = get_project_slug()
+    marker_dir = Path('/tmp/claude-rule-markers') / slug
+    marker_dir.mkdir(parents=True, exist_ok=True)
     marker_file = marker_dir / f'{session_id}.marker'
 
     last_line, _ = read_marker(marker_file)
@@ -452,8 +501,8 @@ def handle_stop(hook_input):
     invocation_ts = datetime.now().strftime('%Y%m%d-%H%M%S')
     invocation_id = f'{session_id}-{invocation_ts}'
 
-    # Fast: spawn conversation review agent first
-    if len(conversation_snippets) > 0:
+    # Fast: spawn conversation review agent first (if enabled)
+    if settings['conversationReflection'] and len(conversation_snippets) > 0:
         conv_context = build_conversation_context(conversation_snippets, modified_files)
         conv_context_file = marker_dir / f'{invocation_id}-conversation.context'
         conv_context_file.write_text(conv_context)
@@ -466,26 +515,27 @@ def handle_stop(hook_input):
             NOTIFICATION_FILE=str(conv_notification_file),
             PROJECT_DIR=project_dir,
         )
-        spawn_claude_agent(conv_prompt, conv_log_file, project_dir)
+        spawn_claude_agent(conv_prompt, conv_log_file, project_dir, model=settings['promptModel'])
 
     # Slow (~10s): check for stale rules last — if the hook timeout kills us
     # here, the conversation agent and marker are already handled
-    stale_rules = get_stale_rules()
-
-    if len(stale_rules) > 0:
-        stale_context = build_stale_rules_context(stale_rules)
-        stale_context_file = marker_dir / f'{invocation_id}-stale.context'
-        stale_context_file.write_text(stale_context)
-
-        stale_log_file = marker_dir / f'{invocation_id}-stale.log'
-        stale_notification_file = marker_dir / 'rule-notification-stale.md'
-        stale_prompt = load_prompt_template(
-            'stale-rules-prompt.txt',
-            CONTEXT_FILE=str(stale_context_file),
-            NOTIFICATION_FILE=str(stale_notification_file),
-            PROJECT_DIR=project_dir,
-        )
-        spawn_claude_agent(stale_prompt, stale_log_file, project_dir)
+    if settings['ruleMaintenance']:
+        stale_rules = get_stale_rules()
+
+        if len(stale_rules) > 0:
+            stale_context = build_stale_rules_context(stale_rules)
+            stale_context_file = marker_dir / f'{invocation_id}-stale.context'
+            stale_context_file.write_text(stale_context)
+
+            stale_log_file = marker_dir / f'{invocation_id}-stale.log'
+            stale_notification_file = marker_dir / 'rule-notification-stale.md'
+            stale_prompt = load_prompt_template(
+                'stale-rules-prompt.txt',
+                CONTEXT_FILE=str(stale_context_file),
+                NOTIFICATION_FILE=str(stale_notification_file),
+                PROJECT_DIR=project_dir,
+            )
+            spawn_claude_agent(stale_prompt, stale_log_file, project_dir, model=settings['promptModel'])
 
 
 def handle_user_prompt_submit(hook_input):
@@ -495,6 +545,12 @@ def handle_user_prompt_submit(hook_input):
     marker file is stale (transcript has lines beyond the marker). If so, spawns a
     rule-reflection agent focused on the interruption.
     """
+    settings = load_memory_settings()
+
+    # Interruption detection is part of conversation reflection
+    if not settings['conversationReflection']:
+        return
+
     session_id = hook_input.get('session_id', '')
     transcript_path = hook_input.get('transcript_path', '')
     follow_up_prompt = hook_input.get('prompt', '')
@@ -502,8 +558,9 @@ def handle_user_prompt_submit(hook_input):
     if not session_id or not transcript_path:
         return
 
-    marker_dir = Path('/tmp/claude-rule-markers')
-    marker_dir.mkdir(exist_ok=True)
+    slug = get_project_slug()
+    marker_dir = Path('/tmp/claude-rule-markers') / slug
+    marker_dir.mkdir(parents=True, exist_ok=True)
     marker_file = marker_dir / f'{session_id}.marker'
 
     last_line, was_stop = read_marker(marker_file)
@@ -561,7 +618,7 @@ def handle_user_prompt_submit(hook_input):
         NOTIFICATION_FILE=str(notification_file),
         PROJECT_DIR=project_dir,
     )
-    spawn_claude_agent(prompt, log_file, project_dir)
+    spawn_claude_agent(prompt, log_file, project_dir, model=settings['promptModel'])
 
 
 def main():