conon.ai

conon.ai/Tips

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.

AdvancedAGENTSClaude Code

Why it works

The docs state it plainly: a fresh context reviews better because it isn't attached to code it just wrote. Two parallel sessions on one version-controlled project — one builds, one reviews cold — recreate the author/reviewer split real teams pay two salaries for. The builder defends; the fresh session just reads what's actually there.

How to do it

  1. Precondition: the project is under version control (isolated copies per session come free).
  2. Session A (name it 'builder — feature X'): builds the feature as usual.
  3. When A says done, open Session B fresh: 'reviewer — feature X'.
  4. Give B the cold brief: 'review the latest changes: real errors, risky assumptions, broken cases.'
  5. Bring B's findings back to A to fix — or let B fix directly if they're small.
  6. Rename both sessions immediately; two unnamed parallels become indistinguishable within the hour.

Copy this

prompt
You're the reviewer; a different session wrote the recent changes. Review the latest diff cold: real errors, unhandled cases, assumptions that could be wrong. You didn't write this — don't defend it.

What to watch for

  • Asking the AUTHOR session 'are you sure it's good?' gets author-grade reassurance — the value is in the fresh context, not in asking twice.
  • Without version control, parallel sessions can genuinely collide in the same files; the isolation is a feature of the baseline, not of sessions per se.

Sources

Original: conon.aiDocumentation: code.claude.com

Read next

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.
Claude Code
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
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 →