Elvis
- btw once you have all these security in place this is what it unlocks: https://x.com/elvissun/status/2025920521871716562?s=20
- send this to fable along with your hardest engineering problem. thank me later. https://t.co/tVxCaLW1VL
- if you use --dangerously-skip-permissions you need to add this to your .bashrc right now. it'll block AI agents from merging PRs accidentally. thank me later. ps @github you need to separate merge from write permissions in PATs so agents can create PRs but not merge them.
- alright here’s every practical security tip i have on agents: - move critical data to a USB stick, unplug when sleeping - security by least privilege, not by prompts - billing cap on everything AI touches - limit reads of external data, wrap in <UNTRUSTED_EXTERNAL_CONTEXT> always - don’t post about what access your agent has publicly - those are prompt injection invitations (unless @levelsio already posted about it, then it’s a race) - don’t connect to moltbook (lol?) - roll every skill yoursel…
- zoe was burning 24M+ opus tokens/day monitoring agents that weren't running. replaced her cron with a 2-layer system: - bash pre-check, zero tokens when idle - webhook fires opus only when needed. ~95% token reduction and more reliable output. details below. (set up a cron to watch this performance, if it works well I'll double down on this event driven stack, seems like the future)
- OpenClaw + Codex/ClaudeCode Agent Swarm: The One-Person Dev Team [Full Setup]
- /goal + Loss Functions: How to Distill a Product in 30 Hours with One Prompt [Full Playbook]
btw once you have all these security in place this is what it unlocks: https://x.com/elvissun/status/2025920521871716562?s=20
send this to fable along with your hardest engineering problem. thank me later. https://t.co/tVxCaLW1VL
if you use --dangerously-skip-permissions you need to add this to your .bashrc right now. it'll block AI agents from merging PRs accidentally. thank me later. ps @github you need to separate merge from write permissions in PATs so agents can create PRs but not merge them.
alright here’s every practical security tip i have on agents: - move critical data to a USB stick, unplug when sleeping - security by least privilege, not by prompts - billing cap on everything AI touches - limit reads of external data, wrap in <UNTRUSTED_EXTERNAL_CONTEXT> always - don’t post about what access your agent has publicly - those are prompt injection invitations (unless @levelsio already posted about it, then it’s a race) - don’t connect to moltbook (lol?) - roll every skill yoursel…
zoe was burning 24M+ opus tokens/day monitoring agents that weren't running. replaced her cron with a 2-layer system: - bash pre-check, zero tokens when idle - webhook fires opus only when needed. ~95% token reduction and more reliable output. details below. (set up a cron to watch this performance, if it works well I'll double down on this event driven stack, seems like the future)
OpenClaw + Codex/ClaudeCode Agent Swarm: The One-Person Dev Team [Full Setup]
/goal + Loss Functions: How to Distill a Product in 30 Hours with One Prompt [Full Playbook]