cyberAlchemyAI

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

Close a session and create a governed session node under sessions/.

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

Checklist for splitting changes into commit groups and writing commit messages — use at commit time.

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

Use when creating or revising a discovery document before DomainSpec authoring or implementation planning, to connect the broader project objective, business context, intended change, evidence, design direction, and technical specifications.

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

Create Mermaid structural diagrams with concise business metadata, show them for user review, and save the confirmed source under output/diagrams. Use for process flows, state transitions, sequences, dependency maps, hierarchies, containment maps, timelines, causal maps, and relationship maps.

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

Select, apply, and compose epistemic, systemic, and categorical perspectives over an object without requiring structured packets or schemas. Use when explanation routing, research, review, or design needs evidence-aware analysis before a human-facing result.

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

Write or review a human-facing low-resolution explanation with the minimum distinctions a specific reader needs. Use for orientation in chat or standalone text, or to identify premature detail and unsupported claims.

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

Write or review a human-facing medium-resolution explanation that lets a specific reader predict, operate, troubleshoot, compare, or decide. Use for conversational or standalone operational understanding beyond basic orientation.

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

Route repository work through installed Arcanum capabilities and execute validated capability-bound dispatches through host-native operations.

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

Creates or revises the informational research-initial-definitions.md required before governed research begins. Use when opening a research topic or documenting its context, purpose, organized refinable research questions with evidence obligations, confirmed constraints, existing evidence, and known gaps without…

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

Run governed, evidence-backed research through internal or external source work, tensioned multi-agent synthesis, skeptic gates, and cited findings. Use for research questions, precedent sweeps, multi-perspective audits, falsification, or synthesis that exceed a direct inline lookup. Every governed research dispatch…

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

Choose low, medium, or high resolution for a human explanation based on what a specific reader needs to understand or do, then execute the corresponding installed writer. Use for explanations in chat or standalone texts, explicit resolution requests, and writer redirects.

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

Red-team existing skills, constitutions, code, schemas, plans, or documents and return verified, severity-ranked change requests. Use when the target already exists and needs adversarial fidelity, correctness, ownership, operability, or abuse-resistance review. Use research instead when the question is whether a new…

cyberAlchemyAI/Arcanum

Agent Claude Code

Execute one bounded Arcanum stage and return a telemetry receipt.

cyberAlchemyAI/Arcanum

Hook Claude Code

Runs before the agent uses a tool for Write, Edit, Write, Edit, MultiEdit, NotebookEdit, Bash and PowerShell tool calls, executing skill-guard.cjs and enforce-append-only-dispatch.cjs via node (2 commands). From cyberAlchemyAI/Arcanum.

cyberAlchemyAI/Arcanum

Settings file Claude Code

Agent settings declaring 1 hook event (PreToolUse).

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

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 legacy compatibility and are not generated by…

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

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.

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

Init-time anti-bias gate. Before the human confirm, two independent agents verify a proposed dispatch sheet is genuinely tensioned (validator-check Tests 1–4); the sheet reaches the human only if BOTH pass — any reproval or disagreement returns it to the strategist. Gate infrastructure: not itself a dispatch, not…

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

Use when converting an Arcanum work-pack task or SWU into a strong native Codex /goal command with outcome, verification surface, constraints, boundaries, iteration policy, and blocked stop condition.

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

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

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

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

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

Author or evolve an invocable Claude Code skill (SKILL.md) through a guided interview — gate whether it should be a skill, draft the routing description, set naming and frontmatter, write a dense body, self-check and verify it fires. Use when asked to create, scaffold, write, design, or edit a skill or slash-command.

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

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

cyberAlchemyAI/Arcanum

Skill Claude CodeCodex

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