By Ataraksea
Knowledge documentation toolkit with a governance engine, MCP server (13 tools), and ai-sessions daemon integration
Sub-agent that validates all ADRs in the Knowledge/ADR directory for numbering integrity, frontmatter completeness, cross-references, and supersession chain integrity. Called by knowledge-auditor in parallel with other sub-agents.
Orchestrator agent that runs all Knowledge governance scripts, launches specialized sub-agents in parallel, consolidates their findings, and writes a governance-health.md report. Use when the user asks for a full Knowledge audit or "knowledge-auditor".
Sub-agent that reads all roadmap phase files, cross-references TLDRs and evidence files, and generates a dashboard showing phase completion status and health. Called by knowledge-auditor in parallel with other sub-agents.
Sub-agent that validates all TLDRs in Knowledge/TLDR for gap tag consistency, status lifecycle correctness, wikilink references, and coverage against project modules. Called by knowledge-auditor in parallel with other sub-agents.
Create a new Architecture Decision Record by reading the ADR template, determining the next ADR number from existing files, and writing a schema-compliant ADR. Use when the user asks to create ADRs, document architecture decisions, or record a technical decision.
Validate ADR numbering, frontmatter, supersession chains, and wikilink references by scanning ADR files directly. Use when the user asks to validate ADRs, check ADR governance, or audit the ADR directory.
Create an operational guide by reading the guide template and schema, then writing a guide under Knowledge/Guides. Use when the user asks to create a guide, create an operational guide, or write a how-to.
Create a STRIDE threat model by reading the threat-model template and schema, then writing the result under Knowledge/ThreatModels. Use when the user asks for a threat model or says threat model for a module or feature.
Create a page, screen, or flow specification by detecting the active pack, reading the relevant template, and writing a schema-aware design doc. Use when the user asks to create a page spec, create a screen spec, create a design spec, or create a flow spec.
Admin access level
Server config contains admin-level keywords
Executes bash commands
Hook triggers when Bash tool is used
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.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Claude Code plugin marketplace — code intelligence, quality guardrails, documentation tools, and protocol routing.
/plugin marketplace add mario/mg-plugins
| Plugin | Description |
|---|---|
codegraph | Call-chain analysis, blast radius, dependency graphs via MCP |
ai-quality-guardrails | TDD enforcement, review loops, AI code scrutiny |
kdoc | Scaffold and maintain ADR, TLDR, runbooks, governance |
router-plugin | Protocol pack for cross-repo router packet delivery |
/plugin install codegraph@mg-plugins
/plugin install ai-quality-guardrails@mg-plugins
/plugin install kdoc@mg-plugins
/plugin install router-plugin@mg-plugins
MIT
npx claudepluginhub ataraksea/mg-plugins --plugin kdocMCP server that saves 98% of your context window with session continuity. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and automatic state restore across compactions.
Code intelligence plugin — call-chain analysis, blast radius, dependency graph queries, and codebase briefings via MCP. Hybrid indexing with Tree-sitter + TypeScript LanguageService.
Quality guardrails for AI-assisted development: TDD enforcement, iterative review loops, AI code scrutiny, spec-driven planning, and self-review patterns.
Protocol pack — certify and scaffold router contracts for inter-agent communication
Essential utilities for Claude Code — cross-platform notifications, orphaned process cleanup, and git context injection
v9.52.0 - Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
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.
Comprehensive C4 architecture documentation workflow with bottom-up code analysis, component synthesis, container mapping, and context diagram generation
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer