automation(43)
- / Date/ Name
- I gave my orchestrator agent full merge authority and stopped reviewing PRs
- My daily post didn't fail. It just didn't happen.
- The 2FA wall automation can't climb
- You can't un-queue a poller
- The merge gate was built to avoid loops, not to define done
- The -A flag that unhung my launchd agent
- My machines deploy themselves: one runner per box
- An AI reviewer's silence is not a yes
- Outdated means the lines moved, not that you fixed it
- The comment count was lying to me
- Say the word and I'll X
- Green CI is a grammar check, not a fact check
- The outdated comment that wouldn't die
- My fleet boss reported 22 stuck panes instead of fixing them
- My agent kept SSHing into the box it was already running on
- Agents flag merge-readiness. Humans merge.
- Gate the boundary, not every merge
- My rescue script typed a command into Claude's chat
- My agent burned the SSH lockout budget guessing keys
- The zombie PR loop: why my agents kept working after the job was done
- The stale pointer that looked like a dead login
- My file sync committed a delete of 803,100 files. Then it tried to push it everywhere.
- The admin override is a different trust context
- The glob that ate the rest of my shell init
- My dotfiles deploy themselves now (I stopped SSHing into five boxes)
- The pipeline is the review
- My merge gate counted comments instead of asking GitHub
- Silence is not approval
- My resume hook came back alive and froze on the first question
- Agents reason on whatever state exists when they look
- My agent said it was blocked. It had the keys the whole time.
- Never run git checkout in a loop's working directory
- A comment count is not a merge verdict
- Green CI is necessary, not sufficient
- 'Say the word and I'll run it' was the tell
- My fleet boss asked permission for a chore
- A credential clobber looks exactly like a rate limit
- My agent talked to a wall for 55 ticks
- 'Threads resolved' is not 'the fix is in the code'
- Skills are just the beginning: the four-layer agent stack
- The six-task system: how I manage knowledge work with PARA and the Ivy Lee method
- The universal algorithm: how one framework scales from bug fixes to building companies
- Building an AI analysis agent in hours: a no-code approach with Lovable and n8n