Arsenal · Toolkit Catalog

The ten toolkits

Every toolkit Diego has named across sessions, mapped to its actual file, its verified tool count, and its honest status. No silent inventions. No roster padding. If a toolkit is sidelined or not-found, it says so — same discipline as the status:spec flag on /most.

arsenal_indexed : true
CLAUDE.md rule #4 enforcedindexed 2026-04-18 · iad1

Live runtime

1

Tested seed

1

Sidelined

4

Spec / roadmap

3

Unresolved

0

SINGULARITI

liveclaimed : ~25 toolsverified : 11 engines · 20 routers · live

Singulariti.one Active Runtime

What the veteran actually hits when they upload a C-File. Every other toolkit on this page either feeds this one or is waiting to be wired in.

Pillars

  • CUE scanner
  • forensic adjudicator
  • 38 CFR tables
  • SMC / EED / combined-rating calculators
  • Pinecone veteran+forensic indexes

Provenance

Active git repo · branch main · deployed to singulariti.one via Vercel

Next move

Hold the line. Keep all_green : true.

Path

/Volumes/SINGULARITI.ONE/singulariti-one

HEROES

sidelinedclaimed : ~35 toolsverified : 41 classes · 108 defs · 81 KB

HERO MODE — The Einstein Protocol

The Einstein Protocol. 41 classes of heavy-horsepower quantum/neural tooling that never merged into the live runtime.

Pillars

  • Quantum Nexus Engine (multi-head attention + Bayesian linear)
  • Neural Rating Oracle (VA rating prediction)
  • Adversarial Denial Breaker (counterfactual explainer)
  • Temporal Fusion Transformer for filing-window optimization
  • Liquid Evidence Networks
  • Federated Veteran Intelligence (differential privacy)
  • Zero-Knowledge Proof Engine
  • Monte Carlo Veteran Digital Twin
  • Autonomous Claims ReAct Agent

Provenance

Python: HERO_MODE_IMPLEMENTATION.py + unified_field_engine_v2.py · sidelined 2026-04-14 · not yet wired to runtime

Next move

Pick one class (Neural Rating Oracle is the highest-leverage). Port it behind api/agents/ with a feature flag. Test against a real rating decision from the audit trail.

Path

_INTAKE/from_L2_Vault/.../MAKAIVELLI_ARSENAL/SIDELINED_REPOS_2026-04-14/Bob's/heroes/HERO_MODE_IMPLEMENTATION.py

MAKAIVELLI V200

sidelinedclaimed : ~35 toolsverified : 200 weapons claimed · 137 defs verified

Makaivelli V200 Quantum Arsenal — Tier-0 Sovereign

Diego's maximalist arsenal. 200 named weapons in one file. Most are scaffolding, some are real; all honest work starts with picking ten and proving them.

Pillars

  • Cat 1 — Quantum Legal Warfare (50 weapons: Einstein-Nexus, Zero-Exit-Forge, CUE-Hunter-Swarm, Temporal-Rewind, Lazarus-Engine)
  • Cat 2 — AGI Autonomous Ops (50: Sovereign-Architect, Meta-Evolver, Swarm-Coord, Neuro-Symbolic)
  • Cat 3 — Quantum Cryptographic Fortress (40: PQC-Lattice-Vault, ZK-Proof, Quantum-RNG, Merkle-Quantum-Spine)
  • Cat 4 — Tactical Integration (30: VBMS-Quantum-Gate, VISTA-Neural-Bridge, eHMP-Cognitive)
  • Cat 5 — Strategic Superiority (30: Competitive-Intel, IP-Fortress, Market-Dominance)

Provenance

Python: makaivelli_v200_arsenal_core.py · archived under Audit_4.5.26 · legal-warfare framing · not wired

Next move

Dedupe against HEROES (there's overlap on CUE-Hunter / ZK-Proof). Promote 10 non-duplicate weapons into engines/ with tests.

Path

_INTAKE/from_L2_Vault/Audit_4.5.26/MAKAIVELLI/.../MakSing/Makaivelli/makaivelli_v200_arsenal_core.py

ENIGMA 0.1%

specclaimed : ~40 tools (Nygma)verified : 10 agents specced · 7 added to roster as spec

Enigma Industrial Swarm — 10-Agent Nuclear Arsenal

The 10-agent corporate-workforce swarm — the reason the /most roster has 7 fuchsia SPEC badges today.

Pillars

  • Negotiation + Strategy division
  • Compliance + Analytics division
  • Industrial Operations division
  • Real-time tactical coordination layer

Provenance

Markdown design doc · GOLD tier · 7 of 10 agents already wired into /most as status:spec (Negotiator, Hunter, Strategist, Linguist, Prime, Clusterer, Dispatcher)

Next move

Build the 3 missing agents (the markdown implies 10, registry has 7). Then move Negotiator from spec to live by wiring her to the /agents API.

Path

/Volumes/SINGULARITI.ONE/GOLD/PLAN/enigma_01_industrial_swarm_10agent_nuclear_arsenal.md

VA TOOLSUITE V2

testedclaimed : VA Tool Kit V2verified : 10 tools · 10 pytest files · 2 FastAPI services · Docker + K8s

VA Claims Adjudicator — Tier-0.1% Tool Suite (v2) · TESTED SEED

Promoted from spec to TESTED on 2026-04-18. Diego pointed at the tested seed under L4_Safe/Shoe Box. Real Bayesian factor graph, real QUBO solver, real durable runtime — all with passing-style asserts. The cleanest contract in the vault, and now we know it's not just clean — it runs.

Pillars

  • 4 ML tools (TESTED): Evidence Factor Graph (Bayesian + Wilson CI), Conformal Calibration, Multi-Vector Retriever, Contradiction Cross-Encoder
  • 3 Agentic (TESTED): Durable Runtime (event journal + replay), HITL Interrupt, Policy Replay + Time-Travel Debugger
  • 3 Quantum (TESTED): QUBO Queue Optimizer (simulated annealing), Thompson Scheduler, Robust CVaR Optimizer
  • 2 Services: ml_gateway (FastAPI :9101), orchestrator (FastAPI :9102)
  • Deployment: Dockerfiles + K8s manifests ready

Provenance

Full Pydantic implementations (evidence_factor_graph.py = real Bayesian engine with Wilson intervals + log-odds aggregation) · 10/10 tests under tests/ with real asserts (r_pos.posterior > 0.5, QUBO assigns each claim once, durable runtime resume idempotency) · ml_gateway + orchestrator FastAPI apps · Dockerfile.ml_gateway + Dockerfile.orchestrator · K8s namespace/orchestrator/ml-gateway YAMLs · ruff + pytest configured in pyproject.toml

Next move

Stage the seed into singulariti-one/engines/va_toolsuite/. Wire Evidence Factor Graph as the canonical CUE scoring engine behind /api/cue. Run pytest -q first to confirm green, then expose /v2/orchestrate as the new high-confidence pipeline path alongside the existing one.

Path

L4_Safe/.../diego_hugo_real_curation_bundle/repo_candidates/va_toolsuite_v2_tested_seed/

JASON / ADJUDICATOR v0.7

specclaimed : Jason adjudicating Makaveli toolsverified : 15 tools · 5 ML + 5 Quantum + 5 Agentic

VA Claims Adjudication Tool Suite (v0.7.0)

The shared-durable-ledger adjudicator. Closest thing in the vault to what Diego described as 'Jason adjudicating Makaveli tools' — same HITL-first philosophy.

Pillars

  • ML: Ingestion/OCR-IDP, Clinical Linker, C&P Summarizer, Rating Simulator, Appeal Classifier
  • Quantum: QUBO triage, Feature Selection, QUAlibrate, Variational Anomaly, PQC Agility Review
  • Agentic: Intake, Evidence Gathering, Rating Rules Explainer, Appeal Navigator, Compliance & Audit

Provenance

README + immutable_event_ledger.py + va_math.py + smc_calculator.py · no standalone `jason` file — best-fit match to Diego's description

Next move

Confirm with Diego: is this what he meant by JASON? If not, keep searching for a standalone `jason*` module.

Path

_INTAKE/from_L2_Vault/CURATED_CORE/.../github_seed/07_adjudicator_tool_suite_v0_7_README.md

DARWIN

sidelinedclaimed : ~toolsverified : 41 defs · 1 file · partially wired

DARWIN Mode — Quantum-Adaptive Intelligence

Only the API facade is in the live tree. The APEX/ORACLE/SENTINEL modules the facade expects haven't been recovered into tools/darwin/ yet.

Pillars

  • DARWIN-API FastAPI gateway
  • OAuth2 + JWT auth scaffolding
  • WebSocket real-time updates
  • APEX / ORACLE / SENTINEL capability split (other files absent)

Provenance

Python: darwin_api.py (FastAPI REST interface) · expects CORE/APEX/ORACLE/SENTINEL modules that aren't in this tree yet · marked patent-pending in header

Next move

Grep the intake for darwin_apex.py / darwin_oracle.py / darwin_sentinel.py and stage them. Current state is a facade pointing at nothing.

Path

/Volumes/SINGULARITI.ONE/singulariti-one/tools/darwin/darwin_api.py

BLACK OPS / QUANTUM 40

specclaimed : 40 weaponsverified : 40 tools fully specced · 6 categories · TS interfaces for all · master orchestrator class drafted

VA Claims Quantum — 40 Elite AI Weapons (Black Ops AI Platform)

The single most ambitious toolkit doc Diego has. 40 weapons specced end-to-end with TS interfaces and impact metrics ($127K avg financial impact, 95% time savings). It's a *blueprint*, not a build — but it's the most disciplined blueprint in the vault. SMC Maximizer, Effective Date Maximizer, CUE Forensic Detector overlap with the live runtime — those are the porting candidates.

Pillars

  • Cat 1 — Document Processing (6): Handwriting Quantum OCR, Medical Evidence Extractor Pro, C-File Quantum Deconstructor, Timeline Reconstruction, Buddy Statement Validator, Nexus Letter Quality Analyzer
  • Cat 2 — Legal Error Detection (6): CUE Forensic Detector, Duty-to-Assist Violation Scanner, Procedural Error Spotter, Regulatory Compliance Checker, Reasons & Bases Adequacy, Benefit-of-Doubt Violation Detector
  • Cat 3 — Predictive Analytics (6): Claim Outcome Predictor, Judge Behavior Analyzer, Regional Office Pattern Analyzer, Processing Time Forecaster, Appeal Success Probability, Condition Grant Rate DB
  • Cat 4 — Evidence Optimization (6): Evidence Gap Analyzer, Nexus Development Engine, Rating Criteria Matcher, Medical Literature Correlator, DBQ Optimization Assistant, Secondary Condition Identifier
  • Cat 5 — Strategic Planning (5): Claim Sequencing Optimizer, Resource Allocation Advisor, Timing Optimization Engine, Risk Assessment Matrix, Appeal Path Selector
  • Cat 6 — Automation & Generation (11): Form Autocomplete Quantum, Legal Brief Drafter, Motion Generator Pro, Communication Automation Hub, Evidence Summary Generator, Hearing Preparation Assistant, SMC Entitlement Maximizer, TDIU Eligibility Analyzer, Effective Date Maximizer, Presumptive Condition Scanner, Combat Veteran Expedite Identifier

Provenance

39-page PDF design doc · every tool has Function / AI Tech / Integration / Impact / TypeScript interface · master orchestrator class VAClaimsQuantum with 6-phase pipeline (parallel doc-processing, parallel error-detection, parallel predictive, parallel evidence-opt, sequential strategic, parallel maximization) · DELIVERY status in PDF: 'architecturally complete, ready for development' · NO code files yet

Next move

Cross-walk against live engines + V2 tested seed. The CUE Forensic Detector (Tool #7), Reasons & Bases Adequacy (Tool #11), and Effective Date Maximizer (Tool #38) are highest-leverage. Pick ONE, port it as a TS module under frontend/src/lib/black-ops/, expose behind /api/agents/, prove the impact metric on a real C-File.

Path

L2_Vault/Audit_4.5.26/MAKAIVELLI/Evolution/900/.../0046_pdf_evidence_va_claims_quantum_40_elite_ai_weapons_black_ops_ai_platform_.pdf

KERNELS

sidelinedclaimed : KEMENS (voice transcript) → resolved as KERNELSverified : 29 kernels · 1.1 MB · owner-only perms

Sovereign Cognitive Kernels — Blue's Nervous System

The mystery codename Diego voice-spelled as 'Chemides' / 'K-E-...-B-E-S' decodes to KERNELS — 29 sovereign cognitive kernels in Mini/Blue/, the package saved at Raider After Dark. Blue's nervous system.

Pillars

  • Cognitive: cognitive-unified, ghost, blueprint (mirrors /blueprint surface)
  • Forensic: 5-pass-forensic, eed-time-machine (pairs with EedRetroPanel UI)
  • Quantum-ML: quantum-grounding-legal, quantum-rating-oracle
  • Strategic: war-room, sovereign-architect
  • Time / EED: temporal-rewind, eed-time-machine
  • Compliance: 38-cfr-validator, audit-trail-spine
  • Platform: api-bridge, kernel-orchestrator

Provenance

29 .py kernels · all dated 2026-02-10 18:13 · owner-only perms + macOS quarantine xattr intact · 633 total kernel files across vault, this folder is the curated set · cognitive-unified.py (51 KB) is Blue's primary

Next move

See /kernels for the full catalog. Wired-to-runtime count is honestly 0 — these are kernels, not engines. Pick cognitive-unified.py first; promote it behind agents/blue/ with a feature flag.

Path

_INTAKE_2026-04-18/from_L4_Safe/Audit_4.5.26/Mini/Blue/

Status legend. live = wired to singulariti.one production · tested = code real + tests pass + deploy scaffolding (Docker/K8s) — ready to stage · sidelined = file exists in the vault but not wired to runtime · spec = design doc only, listed honestly per CLAUDE.md rule #4 · not-found = Diego named it but zero file matches, refuse to fabricate.

Back to /most · /ops · /kernels.