34 boosters for "ai-coding" — open source, verified from GitHub, ready to install
"name": "agent-lint", "description": "Check how well your repo supports AI coding agents.", "homepage": "https://github.com/0xmariowu/agent-lint",
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json", "name": "session-orchestrator", "description": "Session-level orchestration — wave planning, VCS integration, quality gates, persistence, and safety checks",
"name": "swing-skills", "description": "6 cognitive firewalls for AI coding agents. Defends against premature closure, hallucination, anchoring bias, confirmation bias, black-box reasoning, and optimism bias.", "name": "whynowlab",
A parent skill providing code quality assurance strategies that integrates security reviews and systematic debugging for AI-assisted coding agents. Developers using Claude Code will benefit from structured approaches to identifying and fixing code quality, security, and reliability issues.
"name": "programming-as-theory-building-skill", "description": "Programming as Theory Building guidelines for coding agents, grounded in Peter Naur's paper and focused on preserving program theory during code work.", "name": "Programming as Theory Building Skill contributors"
Real Browser MCP enables AI agents to control and automate real Chrome browser sessions with existing logins and state, eliminating the need to re-authenticate or recreate context. Developers building AI coding assistants and autonomous agents benefit from seamless browser automation with full session persistence.
"name": "trueline-mcp", "description": "Truth-verified file editing for AI coding agents via MCP", "url": "https://github.com/rjkaes"
"name": "codealive", "description": "CodeAlive context engine for semantic code search and AI-powered codebase Q&A. Enables AI coding agents to understand entire codebases beyond just open files — search across all indexed repositories, trace cross-service dependencies, discover usage patterns, and
A voice-controlled multi-agent framework for spawning and orchestrating AI workers across machines via CLI, SDK, and Telegram. Useful for developers building complex distributed AI workflows.
"name": "claude-kit", "description": "Configuration factory for Claude Code — 16 skills, 7 agents, 15 stacks, 6 hooks, audit scoring (0-10), and practices pipeline. Bootstrap, sync, audit any project.", "name": "Luis Eiman",
