By appboypov
Workspace management framework: structured markdown workspace for specs, context, memories, and issues with wikilinks, frontmatter relationships, and agent-executable issue decomposition.
Quick-adds a piece of information to workspace memory without interrupting workflow. Infers memory type and scope from content, requires at most 1 question. Use for rapid memory capture during development.
Validates all context files in workspace/context/ for integrity issues including frontmatter completeness, broken wikilinks, alias uniqueness, and bidirectional relationships. Offers per-finding fix or dismiss. Use when verifying context entity health.
Audits local issue files by spawning specialized auditor agents that leave feedback markers, then validates findings and discusses resolution with the user. Use when reviewing created issues for quality, completeness, and adherence to project standards before implementation.
Validates spec completeness and hierarchy integrity by scanning workspace/specs/ for missing relationships, orphaned entities, broken wikilinks, and incomplete frontmatter. Use when reviewing spec quality or verifying hierarchy consistency.
Validates entire workspace integrity across all directories by running 6 validation phases — wikilink resolution, orphan detection, frontmatter validation, hierarchy validation, alias uniqueness, and template compliance. Use when performing a full workspace health check.
Audits issue files for architectural gaps, ambiguities, contradictions, convention divergence, bad patterns, and design principle violations. Use when reviewing issue specifications for architectural completeness before implementation.
Reviews implemented code for architectural gaps, convention divergence, bad patterns, and design principle violations against what was planned in issue files. Use after implementation to verify architectural faithfulness and code quality.
Audits issue files for non-functional requirement gaps including security vulnerabilities, performance concerns, maintainability issues, and technical debt risks. Use when reviewing issue specifications for NFR completeness before implementation.
Reviews implemented code for security vulnerabilities, performance issues, maintainability concerns, and technical debt against what was planned in issue files. Use after implementation to verify NFR compliance and code quality.
Audits issue files for project structure violations, misplaced domain logic, incorrect file placement, naming convention breaches, and unfaithful area-based architecture adherence. Use when reviewing issue specifications for structural correctness before implementation.
Uses power tools
Uses Bash, Write, or Edit tools
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.
A Claude Code plugin marketplace providing workspace management tools for structured markdown workspaces with specs, context, memories, issues, wikilinks, frontmatter relationships, and agent-executable issue decomposition.
Add to your Claude Code project as a plugin:
claude plugins add appboypov/pew-pew-plugins
/create-ws-issues
Decomposes a problem into structured issue files using typed templates and hierarchy rules.
/audit-ws-issues
Spawns specialized auditor agents to validate issue quality before implementation.
/develop-ws-issues
Orchestrates iterative chunk-based implementation with review cycles.
/review-ws-issues
Reviews implemented code against issue specifications with specialized reviewer agents.
pew-pew-plugins/
├── agents/ # 10 specialized agents (5 auditors + 5 reviewers)
├── commands/ # 4 workflow commands (create, audit, develop, review)
├── skills/
│ ├── workspace-issues/ # Issue decomposition framework
│ ├── workspace-context/ # Workspace structure and conventions
│ ├── workspace-evals/ # Eval system with auto-fix
│ └── workspace-meta-data/ # Tracker metadata management
├── templates/ # 19 typed issue templates
└── example/ # Example workspace structure
├── context/
├── issues/
├── memories/
├── specs/
└── templates/
The example/ directory contains a sample workspace structure showing how specs, context, memories, and issues are organized. Use it as a reference when setting up your own workspace.
Contributions welcome. Fork the repo, create a feature branch, and open a pull request.
MIT
npx claudepluginhub appboypov/pew-pew-plugins --plugin workspace-managementClaude + 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.
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.
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.
Make your AI agent code with your project's architecture, rules, and decisions.
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.