v0.9.21 · MIT
See where your AI spend goes - by task, tool, model, and project
— · no license
368 AI skills, 76 expert agents, and 859 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, and research. Installs on Claude Code, Cursor, Codex, Gemini, Copilot, and 6 other AI assistants.
v0.14.0 · MIT
Native DeepSeek Harness tools for an Obsidian wiki vault: wiki_query, wiki_write, and wiki_lint implement the mechanical core (path routing, delta tracking, index/log bookkeeping, health checks) of the wiki skill suite.
v0.2.0 · MIT
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
— · MIT
🪝 Claude Code hooks + an installable plugin marketplace: safety, cost, observability, productivity.
— · MIT
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop with structured specification workflow.
v4.9.2 · MIT
Claude Code plugin that tracks token usage, identifies wasted context, and saves 30-50% on API costs. Heatmaps, ROI reports, budget alerts, efficiency scores, git-aware suggestions — all local, zero config.
v2.0.0 · MIT
Claude Code hooks that auto-switch model tier based on task complexity
v0.5.0 · MIT
Claude Code plugin that shows live session status (⚡ running / 💤 idle / 🔴 attention) in your iTerm2 tab title — no config needed, just install and go.
v1.5.10 · MIT
Local-first AI project orchestration workbench and CLI plugin for DeepSeek Harness: approval-gated planning, Git worktrees, task execution, Issues, and auditable evidence.
v0.1.46 · Apache-2.0
A task conductor for Claude Code that gets better the more you use it. Multi-agent orchestration with an evidence contract that BLOCKS instead of asking, gates written as hooks rather than prompts, and a retrospective that learns your repo's rules and tunes its own playbook.
v0.1.1 · MIT
Shorter replies with Claude Code. Save output token spend.
— · Apache-2.0
Local-first AI coding workflow for vibe coders, indie hackers, technical founders and product managers — catch missing tests and safety checks across Claude Code, Cursor, Windsurf, Replit, Lovable and Bolt.new.
v2.0.4-beta · no license
Specification-driven workflow system for AI-assisted development - break large projects into manageable 2-4 hour sessions with 15-30 tasks each.
— · no license
The complete collection of Kiro IDE configs, agents, skills, hooks, and MCP integrations for maximum productivity.
— · MIT
CLI tool that polls GitHub Issues/PRs and delegates work to Claude CLI
v1.0.1 · no license
Run your Calaf recruiting book from chat: firms, people, pipeline, calendar, notes, and prep.
v1.0.3 · MIT
Let Claude Code reach you on Telegram when it finishes work or needs decisions
— · Apache-2.0
A Claude Code plugin for design companies and entrepreneurs. Connect your tools. Get daily briefs. Track your team.
v0.1.72 · MIT
Free MCP server for developers adding human review gates, prompt risk checks, FAQ review, and CRM note safety to AI tools.
v1.0.21 · MIT
Shrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavior in reasoning AI systems.
— · no license
A curated collection of top-tier penetration testing tools and productivity utilities across multiple domains. Join us to explore, contribute, and enhance your hacking toolkit!
— · AGPL-3.0
The agentic workspace where people and agents work together in the loop.
v3.5.0 · Apache-2.0
Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.