Token, cost and cache observability for Claude Code. Wires the SuperBased Observer MCP server plus its session/tool lifecycle hooks. Requires the observer binary already on your PATH (npm i -g @superbased/observer, or pipx install superbased-observer) — this plugin is wiring only and installs no binary.
★not rated 56▲
+4
changed 6d agoA
tokens not measured
Persistent, private, local-first memory for Claude Code. Your agent remembers your code and decisions across sessions — one static binary, no cloud, nothing leaves your machine.
★not rated 56▲
+2 3mo agoA
tokens not measured
originalMIT
Production-ready prompt library for Claude coding agents: 35+ specialist prompts on the APEI cycle, task-routing skill, and reference hooks — covering Skills, MCP, Plugins, subagents, and hooks for the current Claude Code ecosystem.
★not rated 56
changed 1mo agoA
tokens not measured
originalMIT
Skills that give Claude Code the working knowledge of a Project Engineer: split drawing sets and spec manuals, extract schedules, generate submittal logs, tabulate and evaluate bids, draft RFIs and subcontracts, and research building codes.
TradeOS MCP for Claude: agentic technical analysis of XAUUSD, stocks, crypto, and forex with multi-timeframe charts, ticker search, and macro context. Build AI trading agents for 24/7 smart alerts—no coding required. After installation, connect TradeOS and sign in via Settings > Connectors (Claude Code: /mcp).
★not rated 56▲
+7 3d agoA
tokens not measured
originalMIT
Analyze your codebase against Claude Code's production-grade LLM engineering patterns. Covers architecture, prompt engineering, tool design, resilience, security, multi-agent orchestration, and more.
A starter plugin with Korean learning material and configuration templates for Claude Code, a tool for working with code through natural-language instructions.
★not rated 55
changed 1mo agoA
tokens not measured
originalMIT
Persistent Obsidian-based memory for coding agents. Automatically orients from a knowledge vault at session start, navigates project architecture via graph traversal, and writes discoveries back to the vault.
★not rated 55 7mo agoA
tokens not measured
originalMIT
Prose linter and editor skill. /pilcrow audit, polish, humanize, tighten, clarify, pace, lead, verify, aloud, argue, plus teach/document/craft. AI-tell detection is one feature among many.
★not rated 55 5mo agoA
tokens not measured
originalMIT
Starter pack B2 Tech: hooks de segurança, skills de code review e security audit. Pensado para projetos novos com stack Python/Flask + Next.js/TS em GCP.