Download any Arcanum skill on its own.

Use when: mapping a repository architecture and generating or refreshing a reusable architecture pattern inventory package with selective context, concept cards, dependency rules, testing alignment, and observability alignment.

Audit implementation fidelity against a DomainSpec spec and produce a classified alignment report.

Deterministic code<->spec traceability — extract source tags, validate against a schema, and detect drift vs the spec.

Use when: creating, splitting, selecting, composing, validating, or promoting modular constitutions that enforce artifact structure/form without overloading task context.

Use when: starting or operating a link-indexed local Craft project ledger for recursive development contexts, blockers, enablers, decisions, gaps, definitions, next moves, pending-by-node status, validation, and recomposition.

Use when: resolving blocker-level multi-option decisions before planning, implementation, document mutation, or other consequential changes continue.

Use when: maintaining canonical definitions, synchronized indexes, explanatory intuition, and downstream drift checks for critical terms.

Use when: formalizing, routing, validating, promoting, or retiring an Arcanum discipline so a recurring cross-capability practice gets a card, catalog entry, and a hardening route without claiming sigil or spell authority.

Use when: reducing a broad model, architecture, design, implementation plan, or workflow into the smallest coherent concept unit that still fits the user's target context and can recompose into the larger system.

Use when initializing, running, looping, validating, reporting, or observing repeatable profile-aware development experiments for Arcanum spells and sigils through native skill/subagent execution or explicit legacy runtime adapters.

Use when: claiming one GitHub Project issue, refining its context, invoking define/design/plan as needed, executing through Task Session, and opening a linked PR with verification evidence.

Use when: installing or maintaining a repository-local compiled knowledge inventory that lets agents ingest once, index, tag, query, lint, and reuse context across sigils.

Use when selecting and running invoke template validation prompts in Codex, including picking a task by ID, template, complexity, or the next unrun prompt and saving the Invoke Result output.

Derive a typed metric-obligation inventory from a DomainSpec spec's aspect docs (the doc->metrics rule method).

Use when: mapping, distilling, validating, or evolving a governed knowledge vault with roles, confidence, premises, sessions, edge rules, branch-aware ontology, and ontology conventions.

Use when: turning a vague refinement target, design concern, folder, idea, repository area, or existing work-pack into a refined seed, design, or non-executed plan through the Arcanum refinement loop.

Use when: converting research protocols into validated run schemas, JSONL fixture checks, objective/metric calculations, result summaries, and claim-adjudication readiness without running or overclaiming live experiments.

Use when: turning a paper, source corpus, or research question into a governed local research tower with source-first claims, notation bridge, glossary, definitions, distills, related-work map, bridge decisions, residue, and a final learning pack.

Use when: defining or hardening a specification through stressor analysis, desired residue, degradation behavior, attractor discovery, and resilience decisions.

Run a multi-agent parallel investigation to identify cross-layer tensions

Use when: interviewing a greenfield idea, brownfield repository, or mixed project scope into a structured discovery baseline.

Use when: creating, revising, observing, reflecting on, or iterating a sigil through the governed sigil lifecycle. Includes subagent-based observability and telemetry generation.

Use when installing explicit legacy Arcanum Codex command adapters.

Use when: deriving post-run behavior signals from a sigil invocation envelope and appending reusable observability telemetry.

Use when: extracting one reusable sigil capability from a larger or tangled skill, prompt, workflow, command set, or mixed document.

Use when: converting a complete, coherent skill, prompt, command, or workflow into an Arcanum-compliant sigil package.

Use when: designing, installing, validating, observing, or revising a spell that composes multiple sigils into a localized workflow.

Use when: running one-question-at-a-time interviews with pluggable modes, evidence-backed prompts, and artifact updates after each answer.

Generate story-driven STORIES from DomainSpec aspect docs with mandatory slice coverage and a concept-coverage matrix.

Use when: executing one bounded work-pack task or SWU end to end with explicit trade-offs, context building, gate checks, completion criteria, validation, synchronized evidence, and optional runtime handoff delegation.

Deterministically derive a test-obligation spec from a DomainSpec feature's aspect docs (no LLM in the derivation path).

Use when: translating UX research, accessibility standards, market practice, and Playwright browser evidence into validator-safe checks, fixture plans, or evidence reports for finished frontend interfaces.

Use when routing a verification target to status-qualified owner lanes and joining native evidence receipts into a VERIFICATION-WEAVE parent receipt without promoting owner outputs.

Use when: analyzing accumulated sigil observability signals to produce evidence-backed workflow improvement proposals.

Use when: turning user-supplied context about an object, artifact, architecture, codebase, process, or system into a visual layered HTML explanation page with properties, components, flows, dependencies, and evidence boundaries.

Arcanum Bootstrap installs Arcanum into a consuming repository. It creates generated native runtime skill packages for selected host runtimes, `.arcanum/observability/`, and optional `.arcanum/necronomicon/` harness state. Codex slash commands under `.codex/commands/` are lega…

Discovery To Inventory composes `scope-interview`, `feature-glossary`, and `inventory` so early discovery becomes persistent reusable knowledge.

`goal` drives a Craft-backed work graph through an autonomous, fail-closed control loop. It reads the current frontier, classifies each node by risk, routes work to the owning capability, gates closure with audit evidence, stages ledger deltas, and promotes only behind an expl…

Guide a user through a software architecture target by composing context selection, structure inspection, optional translation, explanation sequencing, active-understanding validation, and User-ledger update proposals.

Implementation Readiness composes `implementation-layering`, `decision-gate`, and `task-session` so a rough implementation goal becomes staged, decided, and ready for one bounded execution loop.

Use when: turning development intent into governed define, design, plan, handoff, or refresh artifacts before lifecycle execution.

Necronomicon is the repository-local knowledge harness for Arcanum. Its MVP is an Inventory And Ontology Substrate Loop: answer what the repository already knows, what is source-backed, what is only a candidate, what conflicts, and which owner should handle the next step.

Observed Invocation Loop wraps Arcanum-managed skill, sigil, and spell invocations with a guaranteed post-run observability handoff. It turns each managed invocation into a safe invocation envelope, appends exactly one telemetry signal, updates reflection counters, and routes…

Ontology Harness composes `inventory`, `ontology-vault`, and `context-builder` so a repository can turn vault-like knowledge material into a reusable ontology governance layer.

Publication Research Pipeline composes Arcanum research capabilities into a governed path from research question to publishable paper package. It keeps source understanding, evidence execution, claim adjudication, paper rewriting, and export packaging in separate owner lanes.

`reading-learning-package` composes a personalized learning package from a completed `research-tower` result and source artifacts. It preserves tower evidence as source authority, uses a Whisper-compatible text intent substrate for composition, and emits traceable reading arti…

Repository Harness composes `inventory`, `architecture-pattern-inventory`, and `context-builder` so a repository gains a reusable knowledge substrate, architecture package, and focused task-context retrieval path.

Sigil Maintenance Loop composes `signal-observer`, `workflow-reflect`, and `sigil-development` so reusable sigils improve from usage evidence.

Whisper turns author intent into meaningful text through a governed composition lifecycle. It extracts a small text intent substrate, selects a balanced combination of narrative primitives and techniques, proposes a construction plan, drafts the text, validates the result, and…

The design principle behind Principle 5 (pairwise tension) of the subagents-strategy constitution. Use when designing the angle set for an n≥2 subject group (role investigate or evaluate) so the agents' micro-vectors are structurally opposed and their correlated bias cancels u…

Use when: validating or designing an Arcanum dispatch route that chains sigils, spells, owner capabilities, handoffs, gates, observability, techniques, and optional boundary/evidence contracts.

Use when: installing or verifying the standard sigil observability package in a repository so sigils can append post-run JSON telemetry and reflection state.

Use when converting an Arcanum work-pack task, SWU, or explicitly selected one-shot stream into a compact native Codex /goal command with sidecar context, profile policy, verification surface, constraints, boundaries, iteration policy, and blocked stop condition.

Use when: building a compact, task-ready context pack from selector-level evidence and obligation-linked excerpts.

Use when: creating or updating a concise glossary for a feature, workflow, product area, or bounded project scope from source evidence.

Use when: creating or evolving a project-agnostic implementation layering model for a feature, capability, product workflow, research workflow, infrastructure change, or system improvement. Builds layers from minimum working unit proof to progressive hardening using value/cost…