cto-team
Claude Code plugin · MIT

You stay the CEO.
Claude becomes your CTO.

Plan once, then ship gate by gate. A separate agent checks every gate, and the next one starts only after it passes.

/plugin marketplace add nhattrung0911/cto-team
/plugin install cto-team@cto-team
GitHub
One gate

How one gate runs

Workers build, a verifier checks, a fixer repairs, then the gate passes.

WorkersSonnet, one brief each
Verifierseparate agent, full suite
Fixerrepairs what failed
Passnext gate may start
Step 4 of 4. Gate passed. Only now does the next gate start.
Feature by feature

What changes after you install it

01

CTO plans once, then delivers gate by gate

BeforeOne agent gets the whole plan and drifts

AfterWorkers get one brief each; the next gate starts only after this one passes

Each worker stays on its own small job, and nothing moves on early.

02

Contract-first API

BeforeFrontend and backend each guess the API

AfterOne contract file the CTO owns; workers may not edit it; the verifier checks the app against it

Both sides build to the same API, and the verifier checks the app against it.

03

The CTO splits the team

BeforeYou hand-assign agents; two agents edit the same file

AfterYou pick 1–5 Sonnet workers per gate; the CTO gives each disjoint files

You only choose the team size; the CTO keeps workers out of each other’s files.

04

Blind verifier on every gate

Before“Tests pass”, says the agent that wrote them

AfterA separate agent proves every acceptance criterion, runs the full suite, and breaks one line the tests must catch

The check comes from an agent that did not write the code.

05

No fake tests, no 500s

Beforeassert True slips through; huge input crashes

AfterFake tests fail the gate; every number gets an overflow test

Fake tests are stopped at the gate, and every number is tested for overflow.

v0.1 crashed on a 20-digit amount; fixed from v0.2

06

Opus batch review

BeforeBugs across features are found by users

AfterEvery 3–4 gates Opus reviews the batch

Opus reviews several gates together, not just one at a time.

Found a real race condition the per-gate checks missed

07

Lean on tokens

BeforeLong-lived “member” agents grow huge

AfterEvery agent is one-shot and starts small; Sonnet does most of the work

Small, one-shot agents keep your token cost down.

12k vs 42k start context; 0.9M vs 3.8M tokens per agent

08

ripgrep instead of grep

BeforeSlow recursive grep, noisy output

AfterA hook points agents to ripgrep (faster, respects .gitignore)

Searches run faster and skip what .gitignore excludes.

09

Picks up after a reset

BeforeContext reset = redo or lost work

AfterState lives in docs/cto/; delivery resumes from the last checkpoint

A reset does not cost you the work already done.

10

Report a non-coder can read

BeforeA long chat log

AfterOne HTML report: what works, how to try it, tech stack, architecture diagram, known gaps

You read one page instead of scrolling a chat.

Quality reference: on a 10-task test app every version passed 14/14 hidden tests.

Start in 3 steps

1

Install

Paste these two lines into Claude Code.

/plugin marketplace add nhattrung0911/cto-team
/plugin install cto-team@cto-team
2

Describe

Tell Claude what you want to build. The CTO plans it with you once.

/cto-team:plan
3

Pick your team

Clear the chat, then hand over the plan. Choose 1–5 Sonnet workers per gate. Delivery runs gate by gate, then you read one report.

/clear
/cto-team:deliver <plan>