pariyar07

Design or modify Markdown knowledge-vault navigation: folder hubs, agent navigation, routing matrices, workstream graphs, optional Bases/view layers, templates, health-check rules, and long-term traversability.

Use when creating, promoting, importing, nesting, or reorganizing scopes inside an existing Markdown knowledge vault with inherited parent and child scope rules.

Validate the structure of an agent-maintained Markdown knowledge vault with deterministic CLI checks for YAML/frontmatter, broken wikilinks, Markdown orphans, scope wiring, and optional Obsidian-compatible view files.

Bootstrap an agentic Markdown knowledge vault for projects, research, learning, life systems, and other long-running knowledge work. Use when creating a new vault, installing the base folder structure, templates, AGENTS.md, CLAUDE.md, Agent navigation files, and optional Obsidian-compatible Bases.

Create or update workspace-level instruction files for code repositories or ordinary project folders, including AGENTS.md, CLAUDE.md, GEMINI.md, local override files, and Ariadne vault-link blocks. Use when a user wants to initialize, repair, or refresh workspace instructions, connect a workspace to a registered Ariadne vault or scope, or make instructions portable across Codex, Claude Code, Gemini CLI, and other agent runtimes without duplicating global discovery.

Run maintenance and health checks for agent-maintained Markdown knowledge vaults: broken links, orphan notes, stale hubs, invalid frontmatter, uncompiled raw sources, stale queues, unresolved questions, optional Base coverage, and health reports.

Close or checkpoint meaningful completed work in an agent-maintained Markdown knowledge vault. Use when the user asks to run Ariadne closeout, make work durable, close the loop, checkpoint this work, capture the outcome, decide whether a chat can close, draft a handoff, or update vault memory after incidents, releases, evaluations, feature work, architecture/product decisions, research sprints, or substantial planning sessions.

Register existing Markdown knowledge vaults for machine-level discovery so cold agents can find long-term knowledge from any workspace. Use when checking, adding, updating, repairing, or removing global vault discovery.

Govern adaptive work by selecting the smallest reliable harness, owning canonical state, negotiating runtime capability, and closing evidence-backed control loops.

Design a bounded execution contract using dynamically generated independent lenses when decision consequence and unresolved uncertainty justify architecture work.

Convert repeated or high-confidence failure evidence into reviewable, scoped, enforceable learning proposals without silently rewriting governance.

Checkpoint, hand off, or retire bounded loop machinery while preserving canonical state, evidence, and governor authority.

Independently test a completion claim against DONE with explicit coverage, provenance, gaps, rerun instructions, and rejection authority.