Plandex is an open-source terminal-based AI coding agent designed for large projects and complex tasks. It handles up to 2M tokens of context, uses a diff sandbox for safe changes, and supports multi-model workflows across Anthropic, OpenAI, and Google providers.
Scanned 6/8/2026
Install via CLI
openskills install agentskillexchange/skills---
name: "Plandex AI Coding Agent for Large Projects"
slug: "plandex-ai-coding-agent-large-projects"
description: "Plandex is an open-source terminal-based AI coding agent designed for large projects and complex tasks. It handles up to 2M tokens of context, uses a diff sandbox for safe changes, and supports multi-model workflows across Anthropic, OpenAI, and Google providers."
github_stars: 15183
verification: "security_reviewed"
source: "https://github.com/plandex-ai/plandex"
category: "Developer Tools"
framework: "Custom Agents"
tool_ecosystem:
github_repo: "plandex-ai/plandex"
github_stars: 15183
---
# Plandex AI Coding Agent for Large Projects
Plandex is an open-source terminal-based AI coding agent designed for large projects and complex tasks. It handles up to 2M tokens of context, uses a diff sandbox for safe changes, and supports multi-model workflows across Anthropic, OpenAI, and Google providers.
## Installation
Requirements and caveats from upstream:
- | **Self-hosted/Local Mode** | • Run Plandex locally with Docker or host on your own server.<br/>• Use your own [OpenRouter.ai](https://openrouter.ai) key (or [other model provider](https://docs.plandex.ai/models/mode...
- For a new project, you might also want to initialize a git repo. Plandex doesn't require that your project is in a git repo, but it does integrate well with git if you use it.
Basic usage or getting-started notes:
- 🧑💻 **REPL mode** with fuzzy auto-complete for commands and file loading. Just run plandex in any project to get started.
- <img src="images/plandex-browser-debug-yt.png" alt="Plandex Browser Debugging Example" width="800">
- bash
- Source: https://github.com/plandex-ai/plandex
- Extracted from upstream docs: https://raw.githubusercontent.com/plandex-ai/plandex/HEAD/README.md
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/plandex-ai-coding-agent-large-projects/)
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.