The person with the idea
Writes what "done" looks like, and files the first tasks. Answers a question when an agent asks one.
Doesn't need to read code, or touch the CLI.
When an agent needs your input →Rollout plan
Two weeks names the shape of a plan you control. It isn't a promise about how fast a task ships.
Who does what
One person can hold more than one of these. What matters is that each one is covered before Day 1.
Writes what "done" looks like, and files the first tasks. Answers a question when an agent asks one.
Doesn't need to read code, or touch the CLI.
When an agent needs your input →Connects the first device and the first repository. One-time setup.
Doesn't need to stay involved once that first setup is done.
How do I add a device? →Signs off where a gate asks for it. Answers agent questions on tasks it operates.
Doesn't need to read every diff. The review stage already checked it.
Approvals & staying in control →The five phases
Read each phase before you start it. What actually happened decides what comes next.
Day 1 · Technical owner
Connect one device and one repository, so an agent has somewhere to work.
Sign-up is invite-only right now. Request access before you start.
Watch for: A device shows Online only while ch device-server keeps running. A closed laptop lid takes it offline.
Done when:
Day 2 · The person with the idea
File one bounded, checkable brief. Watch the herd build it.
Watch for: A vague brief stalls at plan while the agent asks what "done" actually means.
Done when:
Days 3 to 5 · The approver
Learn what each stage's gate checks for you, before you widen the work.
Watch for: An approval gate only holds CodeHerder's own automatic advance. An explicit status command still moves the task.
Done when:
Week 2 · Technical owner
Route more than one task to more than one agent, without them colliding.
Watch for: Two tasks that touch the same files can still collide at review, even from separate worktrees.
Done when:
End of week 2 · The person with the idea
Read what the first two weeks cost and shipped. Then price the next month from your own data.
Watch for: A task that needed rework usually spends across two model tiers.
Done when:
What to hand over first
Small, and easy to check: does the reported bug still happen?
Bounded to one file or package, with a clear, checkable result.
Low risk. A wrong correction is easy for a person to catch and reject.
Routine work, checked against a build or test command you already run.
What to keep back, for now
See /will-it-work and /when-agents-get-it-wrong for the full list of limits, said out loud.
What to measure
No target number. No benchmark. Read your own two weeks. Then decide what good looks like for your team.
ch task show <taskId> prints what a task has cost so far. It also shows where the task stands against any budget you set.
Understanding costs →Every task reports its own change shape: how many files, lines, and directories it touched.
Change shape →Each stage transition is on record, including a send-back into code and which stage sent it there.
How work flows →A blocked task carries a reason: who filed it, and when. Some clear on their own; others need you to act.
Blockers and blocked tasks →FAQ
No. Two weeks names the shape of a plan. Move at whatever pace fits your team. Nothing here times you.
Nobody, unless you set an approval gate yourself. By default, CodeHerder only advances a task on its own at the entry stage. A gate there is where an approval matters most.
Review usually catches it before merge. A send-back into code then runs on a stronger model. A task that keeps failing stops and moves to blocked. A person then decides what happens next.
Day 1 needs a technical teammate for the one-time device and repo setup. Filing and approving tasks after that needs neither.

Tell us what you're building, and we'll get your first device and repo connected.