The four heights
The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.
Execute — do the immediate task
+Add Sandeep and Mara as collaborators with write access to the repo, remove former contractor…
Execute — do the immediate task
+Add Sandeep and Mara as collaborators with write access to the repo, remove former contractor Joel's access, and enable two-factor authentication enforcement for all collaborators. Confirm the changes with the security lead and send Sandeep a short note about branch naming conventions they must follow.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Improve — make it easier to accept
+Before I change collaborator roles, make it easy for the team to accept the new access model:…
Improve — make it easier to accept
+Before I change collaborator roles, make it easy for the team to accept the new access model: surface who will lose or gain write privileges, flag any CI tokens tied to removed accounts, and call out the owners who must be notified. Recommend a brief onboarding checklist for new collaborators that includes required 2FA and the branch naming rules.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Decide — diagnose the stuck moment
+I just removed Joel's collaborator access as his contract ended and immediately a deployment job…
Decide — diagnose the stuck moment
+I removed a contractor's access and a deployment key stopped working.
I just removed Joel's collaborator access as his contract ended and immediately a deployment job failed because its key was tied to his account. I didn't know a CI token depended on him and I can't reach Joel. What should I do now to restore CI and prevent this from happening again during offboarding?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+Every time someone joins or leaves we scramble keys, roles, and notifications; builds fail or…
Become — change the pattern
+Access changes during staff churn break builds and slow reviews.
Every time someone joins or leaves we scramble keys, roles, and notifications; builds fail or reviews are delayed while we untangle access. Over the last six months this cost us a few hours per incident. What routine should we implement for collaborator management and offboarding so access changes are fast, safe, and predictable?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Next to this one
Other code hosting work people do in GitHub.
Every task here came from the work, not from a feature list — which is why the prompts name what you want done and never the button that does it. The tool changes; the work does not.
Copyright © LLOS.ai · 2026 — original pedagogy, voice, and design — all rights reserved.
The rest of the map
Same library, five ways in.