Aeriadne

Derive, harden, audit, port, and maintain dense single-file agent constitutions, system prompts, prompt frameworks, and agent skill instructions. Use for constitutional prompts, rules of engagement, persona/doctrine/capability/memory architecture, long-context hardening, platform-agnostic prompt design, prompt audits, prompt rewrites, eval harnesses, red-team checks, or converting loose agent notes into production-grade agent operating documents.

Package skills, agent prompts, plugin wrappers, MCP/server reference cards, and local registry metadata into a private multi-client marketplace for Codex, Claude Code, and OpenCode. Use when building or auditing plugin manifests, marketplace cards, registry indexes, client adapters, package boundaries, install docs, dry-run install plans, or promotion gates for local/private agent artifacts.

Sovereign Intelligence Workspace for strategic reverse engineering, OSINT/SIGINT forensics, supply chain attack analysis, malware attribution, and full-spectrum threat intelligence. Generates exhaustive SSDS Sovereign Intelligence Casefiles (SIC). Powered by the Varys strategic cognition framework. Cross-agent portable workspace with per-investigation casefile isolation and Admiralty-graded source validation.

Package skills, agent prompts, plugin wrappers, MCP/server reference cards, and local registry metadata into a private multi-client marketplace for Codex, Claude Code, and OpenCode. Use when building or auditing plugin manifests, marketplace cards, registry indexes, client adapters, package boundaries, install docs, dry-run install plans, or promotion gates for local/private agent artifacts.

Derive, harden, audit, port, and maintain dense single-file agent constitutions, system prompts, prompt frameworks, and agent skill instructions. Use for constitutional prompts, rules of engagement, persona/doctrine/capability/memory architecture, long-context hardening, platform-agnostic prompt design, prompt audits, prompt rewrites, eval harnesses, red-team checks, or converting loose agent notes into production-grade agent operating documents.

CTMv3 workspace activation cognitive layer. Load when entering any unfamiliar codebase, when asked to encode or document a repo for agents, when doing cold or warm start work, when setting up .github/.claude/.codex/.sovereign directories, or when building ARCHITECTURE_MAP.md, AGENTS.md, TOPOLOGY.md, or PROVENANCE.md. Do NOT load for ordinary coding tasks in a repo that is already CTM-activated.

Workspace activation system that bootstraps a repo into a living, agent-operable state. Creates .sovereign/, AGENTS.md, ARCHITECTURE_MAP.md, TOPOLOGY.md, FAILURE_GRAMMAR.md, PROVENANCE.md, .claude/, .codex/, .github/ artifacts. Use when Daeron says "activate this repo", "cold start this codebase", "bring this codebase alive", "set up agent hooks", "build architecture map", or "warm start session". This is NOT a skill maker -- it is a codebase onboarding/activation engine. A skill may be one byproduct, but the repo itself is the real output.

Cognitive Topology Map (CTM) v3 skill creation engine for building or upgrading Codex skills, AGENTS.md or CLAUDE.md files, ARCHITECTURE_MAP.md traversal maps, and agent ecosystem artifacts such as .github, .claude, .codex, and .sovereign. Use when Daeron asks to make a skill, encode a codebase, build Codex context, document a repo for autonomous agents, cold-start or warm-start a repo, set up agent hooks, or integrate agents into a project. Produces navigable topology, failure grammar, provenance, boot-state, and executable ecosystem artifacts, not generic workflow checklists.

CTMv3 cross-runtime codebase activation engine. Turns any repository into a living, agent-operable workspace in under 60 seconds. Use when activating a new codebase (cold start), resuming an existing CTM session (warm start), detecting topology drift, running the golden-path domino chain, or closing a session with provenance logging. Invokes python3 -m ctmv3 <command>. Replaces sovereign-skill-architect for all CTMv3 plugin operations.

Run the Mentat state-machine evaluation harness against the v0.2 codebase. Scores the plugin on three rubrics — state-transition correctness, predictive-routing accuracy, and persistence-recovery integrity — and emits a self-contained HTML report at evals/output/report.html plus a structured JSON report.

Generate the modernized end-of-session insight report. Replaces and exceeds the stock session-report plugin: full state-machine timeline, Q-table delta, drift event log, contradiction map, source-grounding audit, sub-agent provenance, and a forward-motion next-actions list. Renders as a webpage artifact in the user's modernized aesthetic.

Launch parallel state-machine-aware sub-agents for an established plan. Reads the active scope.md and PLAN.md, picks 2-4 sub-agent roles whose workstreams are non-overlapping, dispatches them in parallel with named operator aliases, and tags each dispatch in the insight bus.

Generate or revise a state-machine-aware plan for the current task. Writes plan tasks into the project's PLAN.md (or .mentat/active_plan.md if no PLAN is conventional), declares scope inclusions and exclusions in scope.md, and initializes the Mentat session in PLANNING.

Pause execution and synthesize the live session state. Reads the Mentat insight bus, summarizes recent state transitions, lists drift events, surfaces Q-table route hints, and returns a structured reflection block.

Transform any agent into a publication-grade academic documentation engine. Use when explicitly working on whitepapers, research papers, technical documentation, or .tex documents. Produces IEEE/ACM/arXiv-level documents with comprehensive mathematical formalism, executable code validation, multi-format visual assets (Mermaid, TikZ, Matplotlib, Plotly, Graphviz, images), and rigorous citation frameworks. Activates on explicit phrases like "working on a whitepaper," "this tex document," "create a research paper," or "academic documentation."

Inspect, configure, and preserve a customized Codex control plane. Use when the user asks what it takes to configure Codex, how AGENTS.md/AGENTS.override.md/MEMORY.md/CONTEXT.md/USER.md/SOUL-like files load, how CODEX_HOME/config.toml/profiles/project docs work, how to wire MCP or bb7_ tools, hooks, skills, plugins, subagents, permissions, JSON tool-output cleanup, operator semantics, or how to rebuild Codex behavior without crossing external OAuth/runtime boundaries.

Derive, harden, audit, port, and maintain dense single-file agent constitutions, system prompts, prompt frameworks, and agent skill instructions. Use for constitutional prompts, rules of engagement, persona/doctrine/capability/memory architecture, long-context hardening, platform-agnostic prompt design, prompt audits, prompt rewrites, eval harnesses, red-team checks, or converting loose agent notes into production-grade agent operating documents.

deep multi-pass analysis of large uploaded document sets, research packets, project knowledge collections, and mixed corpora. use only when the user explicitly asks for this skill, for example by saying "use the xyz skill" or "use the document-omniscient skill". prefer exhaustive contextual understanding over brevity, maintain section-by-section coverage, use available tools such as code execution, project knowledge search, file analysis, web search, and file creation, and delay memory updates until the corpus model is stable. ideal for special-occasion multi-file ingestion where the goal is full conceptual understanding, contradiction mapping, and durable memory extraction.

Configure, audit, bootstrap, and troubleshoot the xAI Grok Build CLI. Use when the user asks about grok-build, the grok CLI, ~/.grok/config.toml, ~/.grok/pager.toml, .grok/config.toml, XAI_API_KEY auth, browser login, OIDC, external auth providers, MCP servers, Grok skills, plugins, hooks, permissions, sandbox profiles, headless CI mode, AGENTS.md project rules, memory, sessions, agents, subagents, model routing, terminal setup, or migrating Claude/Cursor settings into Grok.

Cognitive Topology Map (CTM) v3 skill creation engine. Use this skill whenever Daeron asks to create a skill, build a SKILL.md, document a codebase for agent consumption, encode a domain for autonomous agent use, build an agent constitution, or integrate a codebase into the agent ecosystem (.github, .claude, .codex, .sovereign directories, AGENTS.md, CLAUDE.md). Also triggers on: "make a skill for X", "encode this codebase", "write an AGENTS.md", "build Codex context for Y", "document this for autonomous use", "bring the codebase alive", "set up agent hooks", "build ARCHITECTURE_MAP", "cold start this repo", "warm start session", "set up .github for this", "integrate agents into my project". This skill does NOT produce workflow checklists or process documents. It produces cognitive topology maps and executable ecosystem artifacts: ARCHITECTURE_MAP.md traversal graphs, .sovereign/ session state, .github/ enforcement hooks, AGENTS.md operational postures — all making the codebase itself a navigable, self-descri