shannon

Shannon Framework

Claude Code plugin for mission-critical domains — replaces subjective AI-development judgments with objective measurements.

Live site: withagents.dev/posts/post-07-prompt-engineering-stack Field journal entry: withagents.dev/posts/post-07-prompt-engineering-stack

---

Version 5.6.0 | Installation | Quick Start | Documentation | GitHub

🚀 V5.6.0 "Comprehensive Quality & Intelligence": 14 new skills, /shannon:health dashboard, advanced testing, security automation! See docs/v5.6/CHANGELOG.md for complete details.

🔒 V6.0.0 "Project-Level Opt-In": Shannon hooks are now silent by default. Per-project activation via .shannon/active sentinel. Activation benchmark F1=1.00 across all 30 skills. See CHANGELOG.md for the full v6 ledger.

---

Activation (Opt-In)

Shannon v6.0.0+ ships with hooks disabled by default in every project. They only fire where you explicitly opt in. This ends cross-project pollution from prior versions.

State	How to set it	Behavior
Active in this project	/shannon:enable (writes .shannon/active)	All hooks fire
Disabled in this project	/shannon:disable (writes .shannon/disabled)	All hooks no-op (sticky off)
Default (no sentinel)	(nothing)	All hooks no-op
Per-shell escape	SHANNON_DISABLE=1 env	Hooks no-op for that shell
Global testing escape	SHANNON_GLOBAL=1 env	Hooks fire everywhere (use sparingly)

Precedence (highest first): SHANNON_DISABLE > SHANNON_GLOBAL > .shannon/disabled > .shannon/active > default-off.

Quick start in a project that should use Shannon:

cd /path/to/your/project
# in Claude Code:
/shannon:enable
# Shannon is now active in this project; other projects unaffected.

To turn it off:

/shannon:disable

---

Overview

Shannon Framework is a Claude Code plugin that transforms AI-assisted development from ad-hoc interactions into a rigorous, quantitative, reproducible methodology. Built for mission-critical domains—Finance, Healthcare, Legal, Security, Aerospace—Shannon replaces subjective judgments with objective measurements throughout the development lifecycle.

What Shannon IS

• Complete Development Methodology: Specification → Planning → Execution → Testing → Reflection
• Multi-Layer Enforcement Architecture: 4 layers (Commands → Skills → Hooks → Core Files) enforcing same principles
• Quantitative Framework: Replace "seems complex" with 8D complexity scores (0.00-1.00)
• Production-Tested System: Built by observing actual LLM violations, creating explicit counters

What Shannon IS NOT

• ❌ Code generation tool
• ❌ Testing framework
• ❌ Project scaffolder
• ✅ Complete methodology for specification-driven development with quantitative rigor

Core Value Proposition

Quantitative Over Qualitative: Replace ALL subjective judgments with objective measurements.

Traditional Approach	Shannon Framework
"Seems complex"	8D complexity score: 0.72/1.00 (VERY COMPLEX)
"Need 3-4 agents"	Formula: complexity × bands = 8-15 agents
"Making progress"	Quantified: 65% complete (+12% this session)
"Tests look fine"	NO MOCKS compliance: 100% or fail
"Architecture aligns"	Alignment score: 87/100 (STRONG)

---

Architecture

4-Layer Enforcement Pyramid