epistemic-matrix

name	epistemic-matrix
version	1.0.0
description	Compile an Epistemic Matrix — the Rumsfeld four-quadrant audit (known knowns / known unknowns / unknown knowns / unknown unknowns) applied to a scope, grounded in evidence on disk. The point is never the four lists; it is the MIGRATION machinery that moves items between quadrants. Use when: "epistemic matrix", "known knowns", "unknown unknowns", "rumsfeld matrix", "map what we know", "what are we blind to", "audit the blind spots", "where do surprises breed". Default scope is portfolio-wide; pass a subsystem to scope it (memory, a client engagement, a product, an instrument). Produces a paired .md + .html artifact.
allowed-tools	["Read","Write","Edit","Bash","Grep","Glob","Agent"]
slug	epistemic-matrix
category	operations
complexity	complex
author	id8Labs
triggers	["epistemic-matrix","epistemic matrix"]
tags	["development","tool-factory-retrofitted"]

Epistemic Matrix

Core Workflows

Workflow 1: Primary Action

1. Analyze the input and context
2. Validate prerequisites are met
3. Execute the core operation
4. Verify the output meets expectations
5. Report results

Compile a Rumsfeld epistemic-matrix audit over a scope. Two of these already exist on disk and define the house style — read them before writing:

• EPISTEMIC-MATRIX-2026-07-08.md (portfolio-wide, the canonical form)
• EPISTEMIC-MATRIX-MEMORY-2026-07-14.md (subsystem-scoped, shows a headline + addendum)

The one rule

The migration is the asset, not the four lists. Every incident becomes an unknown-unknown migrating to a known-known; the machinery that does that migration is what the matrix audits. A matrix that just sorts facts into four buckets has failed. End every matrix on the migration engine and ranked next moves.

Doctrine (what makes this ours, not generic Rumsfeld)

1. Q1 facts carry evidence on disk. Every known known cites a file, a file:line, a dated log, a commit, or a board. No claim without a receipt. This is feedback_verify_before_reporting enforced structurally. If you cannot ground it, it is not a Q1 fact — it is a Q2 question.
2. Q4 is breeding grounds, not items. You cannot list unknown unknowns by definition. You name the grounds where surprises breed — and each named ground must already have produced at least one real surprise. Speculation without a prior incident is not a breeding ground; it is noise.
3. Q3 is anchored to the J-space rule. "An unsigned lesson is functionally unconscious — you can't steer what you can't say." Q3 hunts things already true on disk that no loop reads: dirty trees, inert insights, stale-but-adjudicated bets, tools never run, unsigned lessons. This is the weakest quadrant in most systems and the highest-value one to work.
4. Stale claims are the enemy. A written "fact" that has gone false is worse than an unknown. Flag known-knowns going stale as their own shelf, and treat any load-bearing doc last touched weeks ago as suspect until re-verified.

Workflow

1. Fix the scope and gather ground truth

• Default scope: the whole portfolio. If the user named a subsystem (memory, a client engagement, a product, an instrument), scope to it.
• Enumerate the actual evidence sources for that scope and READ them, do not recall them. Portfolio-wide typically means: ops/GROUND-TRUTH.md, , , , live health alerts, the latest audit, recent DELTA-BRIEF. A subsystem means that subsystem's own instruments (lint output, census, logs, manifests). Run the commands; do not assume their output.