AI agents

I use AI agents inside a strict process. I own the plan, the review and every line that ships. This page shows that process, at ShareTrip and on side projects.

The loop

  1. PlanI approve it first
  2. BuildOne agent, one worktree
  3. ReviewA different provider
  4. FixOne round
  5. CheckReal tests, real results
  6. MergeI do this part

Every change follows the same path. The agents do the middle four steps. The first and the last are mine.

The rules

  1. No agent starts before I approve a plan. The plan says how to split the work and which model does each part.
  2. Each agent works alone. It gets its own worktree, so two agents never edit the same code.
  3. A different provider reviews the code. An agent that wrote a change tends to agree with it.
  4. Checks must really run. A report lists what passed, what failed, and what was skipped.
  5. Agents never merge. They do not push to shared branches. I integrate the work.
  6. Agents never touch production secrets. They inspect a live system only with my approval.

Threads

Skills

A skill is a written procedure that an agent loads for one kind of task. I write mine after I catch myself explaining the same thing twice. Every agent on every machine then follows the same steps.

  • InvestigateExplain the code, the logs or the bug first. An investigation is not permission to fix.
  • Inspect systemsRead databases, logs and storage safely: my approval first, careful credentials, careful data.
  • Verify changeChoose checks that prove the change works when unit tests cannot.
  • OrchestrateDecide when work is worth splitting, which model does each part, and how the pieces come back together safely.
  • ReleasePromote changes across branches and repositories, then verify the deployment.
  • HandoffPack the context of unfinished work so it continues in a new thread or on another machine.

What stays with me

  • The requirements, and the question of what to build.
  • The architecture and the trade-offs.
  • The final read of every diff.
  • The merge, and the result after it.

On my team sheet, the AI agents play false 9: they drop deep and set up the finish. The manager picks the team and owns the result.

Tools

Agents Claude Code · Codex

Workspace T3 Code, with one thread and one worktree for each task

Rules One config repository, shared by every machine

Secrets A password manager, and encrypted bundles between machines

Toolkit, on the home page

Keep scrolling for the next pageKeep scrolling… Abdullah Sarwar Home