By RunemarkLabs
[RuneSmith v0.8.1] Workspace structure manager. Single source of truth for the canonical layout (_INBOX drop zone, plans/active with per-plan tickets/refs, notes, drafts, research, source-docs, archive/superseded, archive/tickets-pushed). /reallocate migrates from any prior shape (auto-snapshots) and pins folder-conventions into CLAUDE.md so future sessions stay coherent. /inbox classifies dropped files and routes them to their canonical homes on consent.
Process files in _INBOX/ - classify each per lib/folder-conventions.md, propose a destination, route on consent. Use when the user says "process inbox", "check inbox", "sort inbox", "what's in the inbox", "deal with inbox", "route these files", or after dropping new files into _INBOX/.
Migrate or initialize the workspace folder structure to the canonical layout defined in lib/folder-conventions.md. Auto-detects existing git repos and migrates them into the CC head; normalizes folder/repo names to kebab-case-lowercase. Writes STRUCTURE.md and refreshes a marker-bounded section in workspace CLAUDE.md so future sessions stay coherent. Use when the user says "reallocate", "fix the structure", "set up the workspace", "migrate to new layout", "tidy the workspace", "bootstrap this project's folders", or starts work in a workspace that hasn't been organized.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub runemarklabs/runesmith --plugin runesmith-workspace[RuneSmith v0.8.3] Developer helpers for the marketplace itself. /help lists installed skills and their natural-language triggers, /plugin-builder scaffolds new plugins, /tech-debt scans the workspace for stale or orphaned artifacts, and /skill-updater propagates convention changes across all skills consistently.
[RuneSmith v0.8.0] Jira ticket and project workflows: create tickets (Task/Story/Bug/Epic) with proper ADF formatting, report bugs with linked Confluence docs, scaffold new Jira projects, and read board status. All operations run against current Atlassian Cloud REST endpoints (no deprecated paths) with explicit consent gates before any push.
[RuneSmith v0.8.0] Atlassian sprint workflow + Cowork↔CC interconnect. /enable wires Atlassian into a project (CLAUDE.md updates, CC-side skill deployment), /start-sprint and /sprint-status manage the active sprint handshake, /check-comms triages the comms folder, /plan-to-tickets converts plans into Jira tickets organized by sprint. CC reads sprints via read-only REST while mutations route through Cowork.
[RuneSmith v0.8.4] Builds the {PROJECT}.cc/ Claude Code monorepo head at your workspace root and installs the project-boundary guardrail that constrains Claude Code sessions to their launch project. /bootstrap-cc writes the CC head (CLAUDE.md, .claude/ scaffolding, comms folder, marker files) and project-level settings; /guardrail installs the user-level permission rules and PreToolUse hook that block cross-project filesystem reads. Idempotent - safe to re-run.
[RuneSmith v0.8.0] Confluence page authoring with proper storage XHTML conversion. Skills cover feature specs, architecture decision records (ADRs), project overview landing pages, append-only decisions logs, known issues trackers, roadmap pages, and session logs. Drafts in markdown locally, converts and publishes on user consent. Optionally pulls plans/active/ as prefill source.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Build and maintain an LLM-curated personal knowledge base in your project — Andrej Karpathy's LLM Wiki pattern, designed to scale to thousands of pages without becoming a context bottleneck. Now with an optional compiled graph layer for typed, provenance-backed relationships.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault (Karpathy's LLM Wiki pattern). v1.7 "Compound Vault" + v1.8 methodology modes close 5 of 5 priority gaps from the May 2026 compass artifact. Ships: substrate alignment with kepano/obsidian-skills, default Obsidian CLI transport, hybrid retrieval (contextual prefix + BM25 + cosine rerank per Anthropic's Sept 2024 research), per-file advisory locking for multi-writer safety, pre-commit verifier agent, AND methodology modes (LYT / PARA / Zettelkasten / Generic) for first-class organizational support no other Claude+Obsidian competitor offers. v1.7.x audit closure: every BLOCKER + HIGH + MEDIUM + LOW finding from the v1.7.0 audit is CLOSED or DEFERRED-with-rationale. Optional DragonScale Memory extension (log folds, deterministic addresses, semantic tiling lint, boundary-first autoresearch).
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Make your AI agent code with your project's architecture, rules, and decisions.