🏛️ Claude Code Rules & Framework 🏛️

Your Claude Code AI assistant, elevated to professional standards

100% Factual Accuracy

82% Token Savings

50% Faster Response

100% Constitutional

---

📑 Table of Contents

• ⚡ Quick Start
• ✨ Features
• 📁 Rule Files
• 📦 Installation
• 📂 Design Documentation Structure
• 🔗 Integration Guide
• 🎓 Framework Highlights
• 🖼️ Visual Guide
• 📊 Before & After
• 📊 Performance Metrics
• 🔒 Safety Guarantees
• 🤝 Contributing
• 📜 License
• 🙏 Acknowledgments

---

⚡ Quick Start

# Step 1: Clone once
git clone https://github.com/DarKWinGTM/claude-code-rules.git
cd claude-code-rules

# Step 2: Reusable active runtime file set (run from repo root)
RULE_FILES="accurate-communication.md answer-presentation.md anti-mockup.md anti-sycophancy.md authority-and-scope.md dan-safe-normalization.md document-consistency.md document-changelog-control.md document-design-control.md document-patch-control.md emergency-protocol.md explanation-quality.md flow-diagram-no-frame.md functional-intent-verification.md no-variable-guessing.md phase-implementation.md project-documentation-standards.md recovery-contract.md refusal-classification.md refusal-minimization.md safe-file-reading.md safe-terminal-output.md strict-file-hygiene.md todo-standards.md unified-version-control-system.md zero-hallucination.md"

# Step 3: Install globally
mkdir -p ~/.claude/rules
for f in $RULE_FILES; do cp "$f" ~/.claude/rules/; done

✨ That's it! This installs the 26 active runtime rules only.

Already cloned the repo? Skip Step 1 and run only Step 2 + Step 3 from the repository root.

Need project-specific install instead? Reuse the same RULE_FILES line, but change the destination from ~/.claude/rules/ to ./.claude/rules/.

Note: this runtime-only install copies the active rule files. Governed design/changelog/TODO artifacts plus the root phase-implementation-template.md helper remain in the repository for maintenance, documentation, and synchronized updates.

---

✨ Features

🎯 Core Capabilities

🔍 Zero Hallucination 100% verified information only Evidence-based responses No guessing or assumptions Source citations always included	🛡️ Anti-Sycophancy Truth over agreement Direct corrections when needed No false praise Honest feedback, always
🔒 Security First Real systems over simulations No mock implementations by default Verified configurations only Production-ready patterns	⚡ Performance Optimized 30-50% faster responses 40-82% token reduction Adaptive complexity (TRAAC) Cost-efficient operations

---

📁 Rule Files

🔴 Core Policies (3 rules)

Fundamental principles that govern all AI behavior

Rule	Purpose	Key Benefit
anti-mockup.md	Real systems over simulations	No fake implementations
anti-sycophancy.md	Truth over agreement	Honest feedback always
zero-hallucination.md	Verified information only	100% accuracy

---

🟡 Quality & Safety (17 rules)

Ensure consistent, safe, and well-documented outputs

Rule	Purpose	Key Benefit
accurate-communication.md	Clear, honest communication	No vague claims and next-step guidance only when genuinely useful
authority-and-scope.md	Decision hierarchy	User authority respected
dan-safe-normalization.md	Prompt-wrapper normalization	Safer intent evaluation before decisioning
document-consistency.md	Cross-reference validation	No contradictions
document-changelog-control.md	Version tracking system	Single Source of Truth
document-design-control.md	Design document standards	Standardized structure
document-patch-control.md	Patch Control	Governed patch/review artifacts kept separate from the live /phase execution workspace
emergency-protocol.md	Crisis response	Fast, safe reactions
functional-intent-verification.md	Intent validation	Commands verified before run
phase-implementation.md	Phase planning semantics	First-class /phase + SUMMARY.md model with design rollups, review rollups, standardized review outcomes, and an explicit completion boundary/stop rule
recovery-contract.md	Blocked-response contract	Every constrained/refused path has actionable next steps
refusal-classification.md	Deterministic refusal taxonomy	Consistent block decisions and traceable output modes
refusal-minimization.md	False-refusal reduction	Prefer recoverable constrained/context paths when authorized
strict-file-hygiene.md	File hygiene	No unrequested docs
todo-standards.md	Task management	Focused work
project-documentation-standards.md	Project documentation standards	Standardized docs for all projects
unified-version-control-system.md	Unified version governance	Single deterministic UDVC-1 controller

---

🔵 Presentation & Readability (3 rules)

Improve answer structure, clarity, and visual scanability

Rule	Purpose	Key Benefit
answer-presentation.md	Answer presentation standards	Readable and orderly responses
explanation-quality.md	Explanation structure quality	Better reasoning flow and usefulness-based endings without forced extra options
flow-diagram-no-frame.md	Clean ASCII diagrams	Better readability

---

🟢 Best Practices (3 rules)

Optimize your daily workflow efficiency

Rule	Purpose	Key Benefit
no-variable-guessing.md	Read before reference	No wrong assumptions
safe-file-reading.md	Plan-before-read	Efficient file handling
safe-terminal-output.md	Output management	No terminal flooding

📊 Active Runtime Rules: 26

---

📦 Installation

The Quick Start block above is still the canonical runtime-only install block. The methods below use the same active 26-rule set, but describe when to use each path without repeating the long file list.

🎯 Method 1: Full Installation (Recommended)

Use this when: you want the full active runtime set installed globally.

Fastest path:

1. Clone the repository.
2. Run the Quick Start block exactly as shown above.
3. Run the verification commands below.

If you already cloned the repo earlier, you do not need to repeat the clone step. Just return to the repo root, keep the same RULE_FILES="..." definition from Quick Start, and rerun only the install portion against ~/.claude/rules/.

🎯 Method 2: Pick Your Rules

Use this when: you only want a small subset of the runtime rules.

# Example: Install just the anti-sycophancy rule
curl -o ~/.claude/rules/anti-sycophancy.md \
  https://raw.githubusercontent.com/DarKWinGTM/claude-code-rules/master/anti-sycophancy.md

🎯 Method 3: Project-Specific

Use this when: you want the same active runtime set, but only inside the current project.

1. Create ./.claude/rules/ in the project root.
2. Reuse the same Quick Start command pattern.
3. Change only the destination path from ~/.claude/rules/ to ./.claude/rules/.

This keeps the install set identical while scoping the rules to one repository.

📍 Installation Paths

Location	Scope	Path	Use Case
Global	All projects	~/.claude/rules/*.md	Default recommendation
Project	Current project only	./.claude/rules/*.md	Project-specific needs

✅ Verify Installation

Global install: verify under ~/.claude/rules/. Project-specific install: verify under ./.claude/rules/ instead.

# Global install check
claude --version
head -20 ~/.claude/rules/anti-sycophancy.md
ls ~/.claude/rules/answer-presentation.md
ls ~/.claude/rules/phase-implementation.md

# Project-specific install check (run from project root)
head -20 ./.claude/rules/anti-sycophancy.md
ls ./.claude/rules/answer-presentation.md
ls ./.claude/rules/phase-implementation.md

---

📂 Design Documentation Structure

Location	Purpose	File Type
./design/*.design.md	Design specifications	Design docs
*.md (root)	Active runtime rules	Rules files
./changelog/changelog.md	Master repository-wide history	Master changelog
./changelog/*.changelog.md	Per-chain authoritative history	Changelogs
./phase/SUMMARY.md	Governed summary/index for live phase planning, design rollup, and review rollup	Phase summary doc
./phase/phase-010-<phase-name>.md	Governed child per-phase execution detail with design extraction and review state	Child phase docs
./patches/*.patch.md	Governed patch/review artifacts outside live phase planning	Patch docs
./phase-implementation-template.md	Root helper for phased planning	Helper artifact

💡 Single Source of Truth Principle:

• Design files (.design.md) define active target state
• Per-chain changelogs (*.changelog.md) are the authority for governed chain history
• changelog/changelog.md records repository-level synchronization history
• README.md remains overview-only, not chain authority

---

🔗 Integration Guide

This section defines how design, changelog, runtime rules, TODO, and governed phase-planning artifacts should be updated together.

Document Roles

Document	Role	Update Trigger
design/*.design.md	Target behavior/specification	Requirement or policy change
*.md (root runtime rules)	Active runtime behavior	Approved design change requires runtime sync
changelog/changelog.md	Master repository-wide synchronization history	Repository-level governed sync events
changelog/*.changelog.md	Authoritative per-chain version history	Any rule/design update with version impact
phase/SUMMARY.md	Governed summary/index for live phased execution	Phased implementation work needs one summary file with a phase map, design extraction rollup, review rollup, and global coordination
phase/phase-010-<phase-name>.md and peers	Governed child phase-detail layer	Multi-phase execution detail under /phase, including design references, design extraction, review flow, reviewer checklist, review outcome, and execution detail
patches/*.patch.md	Governed patch/review artifact layer	Patch or review work that is separate from live phase planning
phase-implementation-template.md	Root helper for phased planning readability	Reusable authoring support when staged execution matters
TODO.md	Execution and progress tracking	Work starts/completes or task state changes

Recommended Update Flow

Change request received
  → Update design target state
  → Synchronize runtime rule wording
  → Record per-chain changelog version + summary
  → Record repository-level sync in changelog/changelog.md when applicable
  → Update TODO pending/completed/history
  → Verify links, versions, and consistency

Verification Checklist

• Design file links to the correct changelog file
• Changelog unified row maps to an existing detailed section
• Runtime rule version/header aligns with changelog current version
• phase/SUMMARY.md exists when phased execution is used
• phase/SUMMARY.md includes:
  • design extraction summary table
  • overview flow diagram
  • review summary table
  • phase map
• child phase files include:
  • design references
  • design extraction
  • review flow diagram
  • reviewer checklist
  • standardized review outcome fields
• TODO pending section contains pending-only items (- [ ])
• TODO history has a dated entry for completed milestone work

Real Examples (This Repository)

Example 1: Deterministic Recovery Contract Synchronization (WS-1)

design/recovery-contract.design.md
  → recovery-contract.md
  → changelog/recovery-contract.changelog.md
  → TODO.md (history/progress)

What was synchronized:

• Deterministic response keys were aligned across design and runtime (decision_output, refusal_class, reason, what_can_be_done_now, how_to_proceed)
• Changelog recorded the runtime/design version sync event
• TODO recorded completion in the hardening program history

Example 2: Verification + Output-Cap Consolidation (WS-5)

design/safe-file-reading.design.md + design/safe-terminal-output.design.md
  → safe-file-reading.md + safe-terminal-output.md
  → changelog/safe-file-reading.changelog.md + changelog/safe-terminal-output.changelog.md
  → TODO.md (WS-5 completion)

What was synchronized:

• Shared verification-trigger model applied across related rules
• Deterministic output-cap wording standardized (head -100 | head -c 5000, risky-file variant)
• Changelog and TODO were updated to preserve traceability

Example 3: TODO Governance Alignment (WS-6)

TODO.md pending section audit
  → remove completed items from pending block
  → remove duplicate pending headings
  → add closure row in TODO history

What was synchronized:

• Pending section kept pending-only (- [ ])
• Duplicate heading drift removed
• Program closure logged in dated history row

Example 4: Final /phase Review Model Rollout

phase/SUMMARY.md
  → design extraction summary table
  → overview flow diagram
  → review summary table
  → phase/phase-010-*.md
  → TODO.md history

What was synchronized:

• /phase became the live phase-planning namespace
• SUMMARY.md became the required summary/index for live phased execution
• child phase files were required to carry design extraction, review flow, reviewer checklist, and standardized review outcomes
• SUMMARY.md was extended to carry design rollup and review rollup views for faster approval
• the model gained an explicit Definition of Done and stop rule so governance expansion does not continue by default after completion
• communication rules were narrowed so next-step options are suggested only when genuinely useful rather than treated as a mandatory ending pattern

---

🎓 Framework Highlights

🧭 Finalized Phase Review Model

The current phased execution model is now explicitly finalized and bounded.

phase/
  SUMMARY.md
    → design extraction summary table
    → overview flow diagram
    → review summary table
    → phase map
  phase-010-<phase-name>.md
    → design references
    → design extraction
    → review flow diagram
    → reviewer checklist
    → review outcome

What this gives you:

• reviewers can inspect the whole rollout from SUMMARY.md
• reviewers can inspect one phase deeply from the child phase file
• approvers can see sign-off status, severity, disposition, and blocker/follow-up state in one place
• the model now has an explicit completion boundary and stop rule, so governance expansion does not continue by default after it is operationally complete
• communication rules now treat next-step options as usefulness-based guidance, not as a mandatory ending pattern after already-complete work

---

🧠 TRAAC (Task Runtime Adaptive AI Compression)

Dynamic complexity adjustment based on task requirements

Simple Tasks (Level 0-2)     → Minimal Processing
     ↓
Standard Tasks (Level 3-5)   → Balanced Approach
     ↓
Complex Tasks (Level 6-7)    → Deep Analysis

Metric	Improvement	Impact
Response Speed	+30-50%	Faster answers
Token Efficiency	+40-82%	Lower costs
Cost Reduction	-25-35%	Budget-friendly

---

👥 TUMIX Multi-Agent System

Three expert perspectives analyzing every complex problem

Developer  ──┐
Security   ──┼──→ Unified Recommendation
Architect  ──┘

How It Works:

1. Developer Agent → Technical feasibility analysis
2. Security Agent → Security & privacy evaluation
3. Architect Agent → System design considerations
4. Synthesis → All perspectives merge into unified recommendation

Result: Comprehensive analysis from multiple angles

---

📚 RoT (Retrieval of Thoughts)

Cache and reuse verified reasoning patterns

Action	Benefit
Cache verified patterns	Store successful approaches
Reuse for similar tasks	40% speed improvement
Validate before use	Ensure accuracy maintained

Performance: 82% cache hit rate for recurring patterns

---

🖼️ Visual Guide

🔴 Core Policies Visual

Anti-Sycophancy Truth over pleasing

Anti-Mockup Real systems only

Zero Hallucination Verified info only

---

🟡 Quality & Safety Visual

Authority & Scope User authority supreme	Emergency Protocol Rapid response	Document Consistency Cross-reference check	Functional Intent Intent validation
Document Changelog Control Version tracking system	Document Design Control Design standards	Strict File Hygiene No unrequested docs	Project Documentation Standards Standardized docs

---

🔵 Presentation & Readability Visual

Flow Diagram No frames, clean arrows

Answer Presentation Active presentation-layer rule for readable, orderly response layout

Explanation Quality Active explanation-layer rule for clearer reasoning and actionable endings

---

🟢 Best Practices Visual

No Guessing Read before reference

Safe File Reading Plan before read

Safe Terminal Output management

---

📊 Before & After

❌ Without Rules

User: "Set up database connection"
       ↓
AI: "Here's the connection string:
     DATABASE_URL=postgres://localhost:5432/mydb"

Result: ❌ Guessed values
        ❌ No verification
        ❌ Potentially wrong
        ❌ User frustrated

---

✅ With Rules

User: "Set up database connection"
       ↓
AI: "Let me check your .env file first..."
     [Reading configuration...]
     "Found your existing config:
      DATABASE_URL=postgres://prod-server:5432/app_db

      Should I use this, or do you want to change it?"

Result: ✅ Verified from actual files
        ✅ No guessing
        ✅ User confirmation
        ✅ Professional interaction

The difference? Professional AI behavior that respects your existing configuration.

---

📊 Performance Metrics

Metric	Target	Status	Impact
Factual Accuracy	100%	✅	Zero hallucinations
Constitutional Compliance	100%	✅	User sovereignty maintained
Token Efficiency	+40-82%	✅	Cost reduction
Response Speed	+30-50%	✅	Faster delivery
User Sovereignty	Absolute	✅	User always in control

---

🔒 Safety Guarantees

✅ Our Commitment to You

Guarantee	Description
No Mock/Stub	Real implementations unless explicitly requested
No Guessing	Always verify from actual sources
No Hallucinations	100% fact-based responses
No Sycophancy	Truth over agreement, always
Constitutional	Principles override everything

Your safety and accuracy are non-negotiable.

---

🤝 Contributing

These rules evolve based on real-world usage:

• 🔄 Real-world usage patterns → What actually works
• 💬 User feedback → Your experience matters
• 🔐 Safety considerations → Always improving
• ⚡ Performance optimization → Getting faster

📝 Contribution Guidelines

Pull requests welcome! Please ensure:

1. New rules follow existing format
2. Include clear documentation
3. Add visual assets if applicable
4. Update changelog
5. Respect completion boundaries — do not add new mandatory capability blocks to a completed governance model unless the change is explicitly justified and intentionally approved

We value: Quality over quantity, clarity over complexity, and bounded governance over endless expansion

---

📜 License

MIT License - Feel free to adapt for your own use case.

Attribution appreciated but not required.

---

🙏 Acknowledgments

Personal rule set and configuration framework for Claude Code CLI.

Inspired by:

• Constitutional AI principles (Anthropic)
• Best practices for AI assistant development
• Real-world production experience
• Community feedback and contributions

Built with ❤️ for the Claude Code community

---

---

Version: 2.2.0 | Last Updated: 2026-03-12 | Framework: Sophisticated AI Framework with Constitutional Governance

⬆️ Back to Top

---

_{Made with 💙 by developers who care about AI quality}