shihwesley-plugins

Research pipeline for Claude Code. One command turns any topic into agent expertise: question tree, zero-context fetch, .mv2 indexing, REPL distillation, skill/subagent generation. Phase 0 searches existing knowledge stores before web. BM25 OR-query preprocessing for Tantivy. Domain-split Apple API stores, coupling assessment, skill graph recommendations. Also runs Python in isolated Docker containers.

Ambient .tech.md generation — auto-documents and tracks freshness of your codebase

Docker sandbox for Python/DSPy execution with memvid-backed knowledge store. 16 MCP tools for code execution, sub-agents, session persistence, and research automation.

TLDR-aware code simplifier — uses AST summaries for context, full reads only for target files. 80%+ token savings on large codebases. Merkle-integrated for O(1) change detection when used with mercator-ai.

Manus-style file-based planning with interactive gates, architecture review, and native task tracking. Supports task-based and spec-driven modes with categorized plan directories (feat/fix/refactor/review/test/polish/general) and auto-detection from user input.

Reverse engineer and extract capabilities from any source — repos, configs, binaries, articles — into your agent workflow. Security scanning, manifest tracking, cross-agent restore.

Ambient dev environment management — auto-switches between dev, test, staging, and prod using Docker containers, sidecars, and task-aware classification.

Merkle-enhanced codebase mapping for AI agents. O(1) change detection, zero-token staleness prevention, parallel subagent analysis. Creates docs/CODEBASE_MAP.md and docs/.mercator.json merkle manifest.