conon.ai

conon.ai/Tips

Scheduled Agents Need An Open Lid

Local scheduled tasks run only while the app is open and the machine is awake — a missed slot is skipped, not postponed. Turn on keep-awake, leave the laptop lid open, and write drift-tolerant instructions: 'if it's already past 5pm, skip today and report that you skipped'. Need lid-closed reliability? That's a cloud task — which can't see your local files.

AdvancedAUTOMATIONClaude Code

Why it works

Local scheduled tasks run on your machine, which means they run at the mercy of your power settings: app closed, lid shut, or machine asleep at the appointed minute — the run is SKIPPED, not postponed. The fix is three habits: keep-awake on, lid open, and drift-tolerant instructions so a late run degrades gracefully instead of doing morning work at midnight.

How to do it

  1. Enable keep-computer-awake in the desktop app settings before scheduling anything.
  2. Create the scheduled task with name, instruction, folder, permission mode, and cadence.
  3. Write the instruction with a drift clause: 'if it's already past 5pm, skip today and report that you skipped.'
  4. Laptop? The lid stays OPEN — closed lid defeats keep-awake, and the schedule dies quietly.
  5. Check the task's run history weekly; skipped runs are marked with the reason.
  6. Need lid-closed reliability? That's a cloud task — which trades away access to your local files. Pick per job.

Copy this

prompt
Daily at 09:00: read yesterday's notes in this folder and produce a five-line summary with any deadlines flagged. If you're running after 17:00 instead, skip the summary and just report that today's run was missed.

What to watch for

  • A missed run looks like silence, not an error — without the weekly history check, a dead schedule can stay dead for a month unnoticed.
  • Two heavy tasks scheduled at the same minute contend; stagger them — the loser of a contention doesn't queue, it stands down.

Sources

Original: conon.aiDocumentation: code.claude.com

Read next

Typed It Three Times? Make A Skill
The third time you type the same procedure is the signal: say 'create a skill that does this' and the agent writes the skill file itself. Then improve it in a loop — run it, note what's off, have it edit its own skill. House rules: 2nd repeated mistake → CLAUDE.md line; 3rd repeated prompt → skill.
Claude Code
Writer Session, Reviewer Session
Run two parallel sessions on one version-controlled project: one builds, the other — with fresh context — reviews. The docs are explicit about why it works: a fresh session isn't attached to code it didn't write, so it critiques honestly where the author session defends.
Claude Code
Send Noisy Research To A Subagent
Any side-investigation that would flood your session — 'which of these fifty files mentions the old pricing?' — goes to a subagent. It reads everything inside its own separate memory and returns three lines; your session's context stays clean for the actual work.
Claude Code
/context Names What Eats The Window
When the agent 'gets dumber toward evening', the window is full — /context shows exactly what by: tools, skills, messages, briefing. Then choose deliberately: /compact WITH instructions on what to preserve (it's an expensive operation — the agent re-reads everything), or the free /clear if the task is done.
Claude Code

We build and operate the systems behind tips like this one — agents, automations and internal tools, shipped into production. See what the studio does →