By yeaight7
Automatically map, analyze, and document your codebase's architecture, tech stack, conventions, and patterns via multi-agent scanning and MCP-backed semantic search.
Explores codebase and writes structured analysis documents. Spawned by map-codebase with a focus area (tech, arch, quality, concerns). Writes documents directly to reduce orchestrator context load.
Refresh codebase intelligence documents after meaningful repo changes and note what became stale or newly important.
Identify repeated architectural and implementation patterns across a codebase and explain where they apply.
Use when starting work in an unfamiliar area of a codebase, spawning a subagent that needs targeted file context, a first search pass missed the relevant file, or the file scope of a task is unclear.
Use when querying, ingesting, or maintaining a local RAG MCP corpus for semantic document retrieval with privacy controls.
Use when connecting to a managed codebase-context MCP/session service, checking stale maps, or safely using MCP-provided repository context.
Use when about to add a new helper, utility, or abstraction, a task sounds like a solved problem, a new external dependency is being considered, or custom code is proposed without checking what already exists.
Use when designing or using MCP-backed structured code search with search, AST query, symbol inventory, and bounded extraction workflows.
Uses power tools
Uses Bash, Write, or Edit tools
npx claudepluginhub yeaight7/agent-powerups --plugin codebase-intelligenceBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Oh My Zsh for coding agents.
Quickstart · Agent Quickstart · Plugins · Installation · Security Model · Contributing
Agent Powerups is an Oh My Zsh-style collection of reusable skills, slash commands, MCP configs, hooks, AGENTS.md templates, and workflows for coding agents.
Today, this repo ships:
apx) with runnable local checksapx plugins inspection (apx plugins list)apx profiles for curated skill/plugin setsNative install is direct for humans. Safety boundaries stay around external tools, secrets, shell profiles, and MCP enablement.
| Path | Status | Notes |
|---|---|---|
skills/ | shipped | Reusable agent workflows such as systematic-debugging and writing-plans |
mcp/ | shipped | Local-first GitHub MCP config with check, smoke, and explicit install commands |
agents-md/ | shipped | Starter AGENTS.md templates |
commands/ | shipped | Review-first command prompts plus safe runnable checks |
hooks/ | shipped | Review-before-use hook recipes plus safe runnable checks |
workflows/ | shipped | Scenario guides |
plugins/ | shipped | Plugins with local-first discovery, validation, native install, and marketplace metadata (apx plugins list) |
scripts/ | shipped | Validation and tool-check helpers for this repo |
examples/ | shipped | Minimal safe setup examples |
If you are an agent working in a repo with Agent Powerups available, route tasks to capabilities yourself instead of waiting to be told:
Match first. On Claude Code the host already lists skills natively — match the task to the narrowest fitting skill (plus obvious fits like no-fluff). On Codex, Gemini, or generic agents, start with apx discover.
Discover the rest — anything not natively loaded (MCP configs, hooks, AGENTS.md templates, installed-only assets):
apx discover "<the user's task>" --target <codex|claude-code|gemini|generic> --json
apx info <chosen-asset> # what it is, when to use it, source path, next action
Read, apply, verify. Read the asset's SKILL.md (or file) before applying it; run apx check <asset> only if it declares external requirements; then verify the result against the task.
Gate risky assets. MCP configs and hooks are review-before-use — surface them for approval, never auto-enable.
npm install -g agent-powerups
apx install claude --full
Workflow-first MCP server design with schema-first tools, context-aware outputs, and evaluation discipline.
Browser, MCP, retrieval, and agent runtime integration skills with conservative setup and safety boundaries.
Quality gates for spec-driven development: adversarial plan verification and structured code review.
Documentation architecture, API reference authoring, ADR writing, readme hardening, and doc quality.
Multi-model orchestration and advisor routing: tri-model review and canonical advisor routing.
Full API lifecycle management for Claude Code. Sync collections, generate client code, discover APIs, run tests, create mocks, publish docs, and audit security. Powered by the Postman MCP Server.
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
v9.54.1 — 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.
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).