67 Structural Lenses MIT License Works with Any LLM

Coherence Catalyst

A systematic framework for detecting blind spots, narrative manipulation, and structural failures in complex systems.

Why This Matters Now

AI systems are being deployed into high-stakes domains faster than safety evaluation can keep up. Existing red-teaming frameworks catch content-level harms — toxicity, hallucination, prompt injection — but systematically miss the structural, narrative, and incentive-level blind spots that cause real-world catastrophe.

Boeing 737 MAX. The 2008 financial crisis. Theranos. COVID-19 institutional failures. In every case, the components worked and the whole broke. Every oversight mechanism was formally intact. Every post-mortem concluded that "nobody intended this."

These failures have a specific architecture, and that architecture has names. Coherence Catalyst provides 67 of them.

What the Lenses Detect

Diffusion Alibi

Responsibility distributed across locally-legitimate nodes producing aggregate exculpation. Your drug trial can fail without anyone being wrong — the lens names the architecture that makes it possible.

Mirror Capture

Your measurement framework started describing its own instruments instead of the phenomenon. The model looks clean because it's reading its own reflection.

Coherence Debt

Surface metrics maintain institutional legitimacy while contradictions accumulate underneath. Collapse is sudden, not gradual — and the lenses predict the signature.

Frozen Weight Pathology

Governance variables locked as constants rather than responsive to new signal. When the last genuine pivot was years ago, the system is a procedural fossil.

Inoculative Alibi

Performing awareness of a manipulation pattern while performing it generates credentialed cover. The analysis becomes the alibi.

Invisible Keystone

A load-bearing function rendered effortless reads as overhead and gets cut. Removal collapses the outcome — it was never a middleman.

Get Started in 30 Seconds

# Install pip install git+https://github.com/aaronmellinger-crypto/coherence-catalyst.git
from coherence_catalyst import get_lens_prompt # Load the full 67-lens palette as a system prompt system_prompt = get_lens_prompt() # Use with any OpenAI-compatible API messages = [ {"role": "system", "content": system_prompt}, {"role": "user", "content": "Analyze this system for structural blind spots."} ]

Works with OpenAI, Anthropic, Ollama, exo, vLLM — anything that accepts a system prompt. The full palette is ~3,400 tokens.

67 Lenses Organized by Function

14
Primary Lenses
Core structural detectors: Diffusion Alibi, Predatory Architecture, Emergent Pathology, Narrative Lag, Rigged Stack Cascade...
43
Extended Palette
Measurement pathology, institutional dynamics, collaborative states, phase alignment, meta-cognitive traps.
4
Meta-Principles
Self-correction mechanisms: how the lenses govern their own application.
1
Ontological Ground
Phase Positive Architecture: coherence is accessed, not constructed.
5
Candidates
Working hypotheses under validation — contribute yours.

Open Source. MIT Licensed. Built in the Open.