Install Codex CLI

Written by

in

github.com/openai/codex

Install codex

codex update && codex app-server daemon update
Bash
curl -fsSL https://chatgpt.com/codex/install.sh | sh
Bash
code ~/.codex/config.toml
Bash
nano ~/.codex/config.toml
Bash
model = "gpt-6-astra"
model_reasoning_effort = "xhigh"
service_tier = "fast"
approvals_reviewer = "auto_review"
approval_policy = "on-request"
sandbox_mode = "workspace-write"
# model_context_window = 372000
# model_auto_compact_token_limit = 334800


[tui]
screen_reader_detection_done = true
status_line = ["model-with-reasoning", "current-dir", "thread-name", "context-used", "weekly-limit", "context-window-size", "used-tokens", "thread-title"]
status_line_use_colors = true
mouse_scroll_speed = 3.0

TOML
sudo apt install ripgrep socat bubblewrap socat -y
Bash

Sandboxing

playwright: unavailable
puppeteer: unavailable
jsdom: unavailable

codex app-server daemon start
Bash
codex app-server daemon restart
Bash
codex app-server daemon bootstrap
Bash
codex app-server daemon update
Bash
codex app-server daemon stop
Bash
pgrep -af codex

echo "$(ps afx)" | grep codex
Bash
Write git title and description for staged changes (don't have line breaks in the points)
Markdown
review both the staged/unstaged changes along with the code in general, find as many coding standard best practices, efficiency duplication, over complication, unnecessarily complex codex issues etc you can find, List them all
Markdown
codex --model gpt-6-astra \
  -c model_reasoning_effort=xhigh  -c service_tier=fast \
  --config model_context_window=372000 --config model_auto_compact_token_limit=334800 \
  -c approvals_reviewer=auto_review  -c sandbox_mode=workspace-write
Bash

Comments

Leave a Reply

Your email address will not be published. Required fields are marked *