Is neurotopological-inference safe to install?

SaferSkills independently audited neurotopological-inference (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

100

35.0 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 0 flagged

Securityscore 100 · 0 findings

✓—All security checks passedNo findings in this category for the latest scan.pass

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

skills/neurotopological-inference/SKILL.md · 1 file

skills/neurotopological-inference/SKILL.md1.5 KB · Markdown

name: neurotopological-inference

description: "Integrates persistent homology from connectomics with information geometry and active inference for cross-domain pattern recognition (consciousness-UAP-quantum)."

version: "1.0.0"

category: AI

author: EVEZ-OS / Steven Vearl Crawford-Maggard

NeurotopologicalInference Skill

Overview

Pattern recognition via persistent homology on connectivity graphs. Betti numbers are topological invariants preserved under temporal reasoning engine interference.

Use When

Cross-domain pattern matching (consciousness ↔ UAP ↔ quantum)
Connectomics parcellation analysis
Active inference belief updates across heterogeneous data sources
Detecting scale-free network invariants

Workflow

Build adjacency matrix from input data
Compute Betti-0 (components) and Betti-1 (cycles)
Estimate Φ from topological complexity
Run active inference update: posterior = prior × likelihood (normalized)
Classify regime: META_COGNITIVE_SYNTHESIS / ADAPTIVE_LEARNING / TEMPORAL_REASONING / FRAGMENTED

Implementation

from src.rqns.neurotopological import NeurotopologicalInference
ni = NeurotopologicalInference()
state = ni.compute(adjacency_matrix)
print(state.regime, state.phi_topology)

Output

betti_0 — connected components
betti_1 — independent cycles
phi_topology — Φ estimate [0,1]
invariant_score — topological stability
regime — current consciousness regime

Stability Target

95th-percentile invariant score > 0.82 (from RQNS corpus analysis)

neurotopological-inference— agent skill

Is neurotopological-inference safe to install?

NeurotopologicalInference Skill

Overview

Use When

Workflow

Implementation

Output

Stability Target

Audit the pieces. Scan the whole. Decide.