[grizmaldi]

"Instead of going through the plan manually, I let Claude Code run terraform plan and then terraform apply".

Doesn't matter if it was you or the bot running terraform, the whole point of a two-step process is to confirm the plan looks right before executing the apply. Looking at the plan after the apply is already running is insane.

[bombcar]

Shoot first and ask questions later! Measure nonce and cut thrice!

[hnthrow0287345]

Surely more and harder leetcode interviews will prevent this from happening

[Eddy_Viscosity2]

More like 'Shoot yourself first and then complain out it later!'

[esafak]

Vibe SRE-ing.

[DrJokepu]

I mean it would be nice if the Claude and Codex CLIs had a setting to default to plan mode, every now and then I’m trying to put together a plan, only to realize that it’s not in plan mode and already making changes.

[bigstrat2003]

You should not, under any circumstances, let an LLM touch the Terraform CLI. It's completely irresponsible to give an error-prone system like an LLM that kind of access.

[colpabar]

This is what I can't get over - who in their right mind would _ever_ give an agent enough access to delete prod data?

[bigfatkitten]

Someone who should be immediately fired.

[BitsAndObjects]

This is the purpose of sandbox environments.

[abirch]

What about

  ~/.claude/settings.json
  {"permissions": {"defaultMode": "plan"}}

[sobjornstad]

Claude at least does: add "permissions": { "defaultMode: "plan" } to your settings.json.

I'll note this only applies to new sessions though – if you do /clear and start working on something else it doesn't re-apply plan mode (I kind of wish it did)

[Sathwickp]

I mean that sentence is basically your RCA