caveman
claudeTalk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Query a grounded architecture model of your codebase over MCP instead of reading files. Bundles the MCP server (auto-registered) and a skill that makes your agent reach for it automatically.
Plugin archmantic from marketplace archmantic in mgionas/Archmantic. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
use-archmanticUse when onboarding to, exploring, or answering questions about a codebase — BEFORE reading or grepping many files to build context. Triggers: "how does X work", "where is Y", "what depends on Z / what does Z affect", "what's the data model / API surface / architecture / main flow", "what does this
/archmantic:architectureSummarize this repository's architecture using the Archmantic model — context, domains, data model, and API surface, grounded in code.
archmantic-explorerRead-only codebase explorer that answers architecture / onboarding / "how does X work" / "what depends on Y" / "what's the data model or API surface" questions by querying the Archmantic model (MCP) FIRST, reading files only as fallback. Delegate codebase-understanding and research tasks here — espe
archmanticruns: npx -y archmantic@latest mcp
node "${CLAUDE_PLUGIN_ROOT}/hooks/nudge.mjs"
node "${CLAUDE_PLUGIN_ROOT}/hooks/subagent-nudge.mjs"
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
AI-powered codebase understanding — analyze, visualize, and explain any project
9 skills · 10 agents · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.