Skip to content

Free · no login · vendor-neutral

What shipped in the coding agents you already run

One briefing across editors, terminal CLIs, and open-source agents.

3 things to decide · 29 tools tracked · source-linked · 54% primary feeds

Which agents do you run?

Tap the ones you actually use. The briefing filters instantly — no account.

Versions, MCP, alerts →

Editors & IDE agents

Terminal agents

Cloud & platforms

What shipped

OpenAI Codex CLIrust-v0.164.0Oct 23, 2026

Save reusable prompts and slash commands in ten numbered `/presets` slots, with a keyboard menu for quick access. (#54380, #54381)

  • Set model, reasoning effort, speed, and permission profiles directly with inline `/model` and `/permissions` arguments. (#54378, #54383)
  • Preview viewed and generated images in the fullscreen transcript on terminals supporting Kitty or Sixel graphics. (#54216)
  • +138 more on the OpenAI Codex CLI page
agentmcpmodelsecuritySource ↗
Worth tracking?

One next step. Copy a prompt into the agent you already use, then approve, defer, or ignore. Nothing auto-applies.

proposalteamP5Worth a lookOpenAI Codex CLI

Save team slash commands in Codex `/presets` slots

Codex CLI rust-v0.164.0 adds ten numbered /presets slots with a keyboard menu, plus inline /model and /permissions arguments. Capture repeatable prompts as presets and switch model, reasoning, speed, and permission profiles without leaving the session.
  1. Upgrade to OpenAI Codex CLI rust-v0.164.0, then run /presets and save the team's repeatable prompts and slash commands into the ten numbered slots via the keyboard menu.
  2. Mid-session, set model, reasoning effort, and speed with inline /model arguments instead of editing config or restarting Codex.
  3. Apply a permission profile with inline /permissions arguments before sending queued prompts so those prompts wait until the pending permission selection resolves.
agentmcpmodelsecurityideRelease source ↗

Your loop

This browser · no sign-in · not shared as “you”

After you run the prompt

Only you can mark this. Agents cannot write your loop.

Your decision stays on this device. A public tally appears after a few votes.

Open full proposal · rationale, actions, and prompts for every agent.

From people who use it

What builders say

  • My first tab every morning. The daily log tells me what changed in Claude Code and Codex before my standup, with the source one click away.
    Ana RuizStaff engineer, building agents

Shared with permission, in their own words. Removed on request.