Skill Claude CodeCodex
Use when: defining or hardening a specification through stressor analysis, desired residue, degradation behavior, attractor discovery, and resilience decisions.
Skill Claude CodeCodex
Use when: defining or hardening a specification through stressor analysis, desired residue, degradation behavior, attractor discovery, and resilience decisions.
Skill Claude CodeCodex
Run a multi-agent parallel investigation to identify cross-layer tensions.
Skill Claude CodeCodex
Use when: interviewing a greenfield idea, brownfield repository, or mixed project scope into a structured discovery baseline.
Skill Claude CodeCodex
Use when: creating, revising, observing, reflecting on, or iterating a sigil through the governed sigil lifecycle. Includes subagent-based observability and telemetry generation.
Skill Claude CodeCodex
Composed Arcanum spell: sigil-maintenance-loop.
Skill Claude CodeCodex
Use when installing explicit legacy Arcanum Codex command adapters.
Skill Claude CodeCodex
Use when: deriving post-run behavior signals from a sigil invocation envelope and appending reusable observability telemetry.
Skill Claude CodeCodex
Use when: extracting one reusable sigil capability from a larger or tangled skill, prompt, workflow, command set, or mixed document.
Skill Claude CodeCodex
Use when: converting a complete, coherent skill, prompt, command, or workflow into an Arcanum-compliant sigil package.
Skill Claude CodeCodex
Use when: designing, installing, validating, observing, or revising a spell that composes multiple sigils into a localized workflow.
Skill Claude CodeCodex
Alias package for interrogation.
Skill Claude CodeCodex
Use when deciding whether work merits a governed multi-agent dispatch and, when it does, proposing, tension-checking, confirming, registering, running, closing, and observing that dispatch through repository-local bindings.
Skill Claude CodeCodex
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.