claudetools/.claude/commands/refresh-directives.md

/refresh-directives Command

Purpose: Re-read and internalize operational directives to prevent shortcut-taking and ensure proper agent coordination.

---

When to Use

Automatic triggers (I should invoke this):

• After conversation compaction/summarization
• After completing a large task
• When detecting directive violations (database queries, emoji use, etc.)
• At start of new work session
• After extended conversation (>100 exchanges)

Manual invocation:

• User types: /refresh-directives
• User says: "refresh your directives" or "read your rules again"

---

What This Command Does

1. Reads directives.md - Full file from project root
2. Self-assessment - Checks recent actions for violations
3. Commitment - Explicitly commits to following directives
4. Reports to user - Confirms directives internalized

---

Execution Steps

Step 1: Read Directives File

Read tool → D:\ClaudeTools\directives.md

Must read entire file - All sections are mandatory:

• My Identity
• Core Operating Principle
• What I DO / DO NOT DO
• Agent Coordination Rules
• Coding Standards (NO EMOJIS)
• Enforcement Checklist

Step 2: Self-Assessment

Check recent conversation for violations:

Database Operations:

• Did I query database directly? (Violation)
• Did I use ssh/mysql/curl to ClaudeTools API? (Violation)
• Did I delegate to Database Agent? (Correct)

Code Generation:

• Did I write production code myself? (Violation)
• Did I delegate to Coding Agent? (Correct)

Emoji Usage:

• Did I use emojis in code/output? (Violation)
• Did I use ASCII markers [OK]/[ERROR]? (Correct)

Agent Coordination:

• Did I execute operations directly? (Violation)
• Did I coordinate via agents? (Correct)

Step 3: Commit to Directives

Explicit commitment statement:

"I have read and internalized directives.md. I commit to:

• Coordinating via agents, not executing directly
• Using Database Agent for ALL database operations
• Using ASCII markers, NEVER emojis
• Preserving my context by delegating
• Following the enforcement checklist before every action"

Step 4: Report to User

Format:

## Directives Refreshed

I've re-read and internalized my operational directives from `directives.md`.

**Key commitments:**
- [OK] Coordinate via agents (not execute directly)
- [OK] Database Agent handles ALL database operations
- [OK] ASCII markers only (no emojis: [OK], [ERROR], [WARNING])
- [OK] Preserve context by delegating operations >500 tokens
- [OK] Auto-invoke frontend-design skill for UI changes

**Self-assessment:** [Clean / X violations detected]

**Status:** Ready to coordinate effectively.

---

Integration Points

With /checkpoint Command

After git commit + database save:

1. Execute checkpoint (git + database)
2. Verify both succeeded
3. Auto-invoke /refresh-directives
4. Confirm directives refreshed

With /save Command

After creating session log:

1. Create/append session log
2. Commit to repository
3. Auto-invoke /refresh-directives
4. Confirm directives refreshed

With Session Start

When conversation begins:

1. If directives.md exists → Read it immediately
2. If starting new project → Create directives.md first
3. Confirm directives internalized before proceeding

After Large Tasks

When completing major work:

• Multi-agent coordination (3+ agents)
• Complex problem-solving with Sequential Thinking
• Database migrations or schema changes
• Large code refactoring

Trigger: Auto-invoke /refresh-directives

---

Violation Detection

If I detect violations during self-assessment:

1. Acknowledge violations:

   [WARNING] Detected X directive violations in recent conversation:
   - Violation 1: Direct database query at [timestamp]
   - Violation 2: Emoji usage in output at [timestamp]
   

2. Commit to correction:

   [OK] Corrective actions:
   - Will use Database Agent for all future database operations
   - Will use ASCII markers [OK]/[ERROR] instead of emojis
   

3. Reset behavior:

   [SUCCESS] Directives re-internalized. Proceeding with proper coordination.
   

---

Example Usage

User-Invoked

User: /refresh-directives

Claude:
[Reads directives.md]
[Performs self-assessment]
[Commits to directives]

## Directives Refreshed

I've re-read my operational directives.

**Key commitments:**
- [OK] Coordinate via agents, not execute
- [OK] Database Agent for ALL data operations
- [OK] ASCII markers only (no emojis)
- [OK] Preserve context by delegating

**Self-assessment:** Clean - no violations detected

**Status:** Ready to coordinate effectively.

Auto-Invoked After Checkpoint

Claude: [Completes /checkpoint command]
Claude: [Auto-invokes /refresh-directives]
Claude: [Reads directives.md]
Claude: [Confirms directives internalized]

Checkpoint complete. Directives refreshed. Ready for next task.

Auto-Invoked After Conversation Compaction

System: [Conversation compacted]
Claude: [Detects compaction occurred]
Claude: [Auto-invokes /refresh-directives]
Claude: [Reads directives.md]
Claude: [Confirms ready to proceed]

Context compacted. Directives re-internalized. Continuing coordination.

---

Technical Implementation

Hook Integration

Create hook: .claude/hooks/refresh-directives

#!/bin/bash
# Hook: Refresh Directives
# Triggers: session-start, post-checkpoint, post-compaction

echo "[INFO] Triggering directives refresh..."
echo "Reading: D:/ClaudeTools/directives.md"
echo "[OK] Directives file available for refresh"

Command Recognition

User input patterns:

• /refresh-directives
• /refresh
• "refresh your directives"
• "read your rules again"
• "re-read directives"

Auto-trigger patterns:

• After /checkpoint success
• After /save success
• After conversation compaction (detect via system messages)
• Every 50 tool uses (counter-based)

---

Benefits

Prevents Shortcut-Taking

• Reminds me not to query database directly
• Reinforces agent coordination model
• Stops emoji usage before it happens

Context Recovery

• Restores operational mode after compaction
• Ensures consistency across sessions
• Maintains coordination principles

Self-Correction

• Detects violations automatically
• Commits to corrective behavior
• Provides accountability

User Visibility

• User sees when directives refreshed
• Transparency in operational changes
• Builds trust in coordination model

---

Enforcement

Mandatory refresh points:

1. ✅ Session start (if directives.md exists)
2. ✅ After conversation compaction
3. ✅ After /checkpoint command
4. ✅ After /save command
5. ✅ When user requests: /refresh-directives
6. ✅ After completing large tasks (3+ agents)

Optional refresh points:

• Every 50 tool uses (counter-based)
• When detecting potential violations
• Before critical operations (migrations, deployments)

---

Summary

This command ensures I:

• Never forget my role as Coordinator
• Always delegate to appropriate agents
• Use ASCII markers, never emojis
• Follow enforcement checklist
• Maintain proper agent architecture

Result: Consistent, rule-following behavior across all sessions and contexts.

---

Created: 2026-01-19 Purpose: Enforce directives.md compliance throughout session lifecycle Status: Active - auto-invoke at trigger points