Plandex CLI Cheatsheet - Terminal Planning AI Coding Agent (pdx)

All Plandex terminal planning AI coding-agent commands in one place — from install & auth to plan/load, tell execution to branch iteration — organized by scenario. Copy and go.

AI CLI·14 commands·Last updated 2026-08-26

Install & Auth 4

curl -sL https://plandex.ai/install.sh | bash
One-line zero-dependency CLI install
export OPENAI_API_KEY=...
Defaults to OpenAI (or OPENROUTER_API_KEY)
plandex
Start the REPL (alias pdx)
pdx
Short alias for plandex

Plan & Load 6

plandex new
Start the first plan in the cwd
plandex load some-file.ts another-file.ts
Add files to context
plandex load src/components -r
Load a whole directory recursively
plandex load src --tree
Load directory layout (file names only)
plandex load src/**/*.ts
Load files matching a glob
plandex load https://raw.githubusercontent.com/.../README.md
Load the text content of a URL

Execute & Iterate 4

plandex tell "add a new line chart..."
Send a task; the agent plans then implements
plandex tell -f prompt.txt
Read the prompt from a file
plandex help
List all commands
plandex <command> --help
Show detailed help for a command

Tips

  • Plandex core is plan-then-implement: changes accumulate in a protected sandbox for review before applying to project files, with built-in version control to roll back anytime.
  • `plandex load -r` loads a directory recursively, `--tree` loads structure only, and `**/*.ts` uses glob — control context precisely and avoid wasting tokens.
  • It defaults to OpenAI but also works with Anthropic Claude, Gemini, Mixtral, Llama, and more via OpenRouter.ai or any OpenAI-compatible endpoint.

FAQ

How is Plandex different from ordinary AI chat coding?

Plandex targets large tasks: changes accumulate in a sandbox for your review before applying; built-in version control rolls back, branches try multiple approaches in parallel, and context stays current automatically.

Must Plandex use OpenAI?

It defaults to OpenAI (needs OPENAI_API_KEY) but also supports Anthropic Claude, Google Gemini, Mixtral, Llama, and more via OpenRouter.ai or any OpenAI-compatible provider.

Official References

Each command links to its official documentation below, so you can verify the latest usage and read deeper.

Maintained by LaoHand

Publicly updated on Aug 26, 2026, continuously proofread against official docs.

Contact Us

Wrong command or description? Send us corrections, business inquiries or product feedback by email.

Contact Us

Edit this page on GitHub

Edit the source file directly and open a PR to improve this cheatsheet.