Chief + Claude Code: Better Together

At a glance

What is Chief?

Chief is an AI-native agent manager. It sits above coding agents like Claude Code and handles everything between "here's what I want" and "here's the shipped result" — planning what to build, figuring out what comes next, dispatching agents across your entire portfolio, and reviewing output before it ships.

You already use Claude Code to implement features. Chief makes Claude Code productive at scale — across every project you manage, with the right agent for each task, executing complex goals end-to-end without you manually breaking them down.

Chief uses a BYOA (bring-your-own-agent) model. You connect your existing Claude Code subscription — no new agent costs, no migration, no lock-in.

What Chief adds on top

1. Plan and execute complex goals in one shot

Claude Code executes tasks — but "implement Stripe billing" still requires you to manually break it into subtasks, sequence them, and prompt Claude Code for each one. Ultraplan addresses some of this within a session but doesn't persist across sessions or coordinate across projects.

Chief provides one-shot execution of complex goals. Give it "implement Stripe billing with usage metering and team plans" and Chief decomposes it into dependency-aware milestones — the schema migration before the API endpoints, the webhook handler before the billing page. Each milestone has acceptance criteria, an implementation plan, and a review gate. You approve the plan once; Chief executes the entire sequence.

The difference: instead of managing ten prompts across five sessions, you manage one goal and one approval.

2. Proactive management that figures out what's next

Claude Code waits for you. Every session starts because you decide to start it, working on what you specified. Between sessions, nothing happens — the project sits idle until you return.

Chief is proactive. It analyzes project state, understands what's been completed, what's blocked, and what's ready to start — then proposes the next milestones. When you approve work in the morning, Chief has already figured out the afternoon's priorities based on what shipped. You make decisions; Chief drives the pace.

3. Scale agents across your entire portfolio

Claude Code works in one codebase at a time. Five repos means five separate sessions, five contexts, five decisions about what to work on — and zero coordination between them.

Chief manages agents across all your projects simultaneously. Dispatch Claude Code to three repos, Codex to two more, and see all progress in one dashboard. Chief tracks what's in flight everywhere, and sequences cross-project dependencies. Your output multiplies with each project you add — without multiplying your management overhead.

4. Mix the right provider for each task

Claude Code uses Anthropic models exclusively. If GPT-5.5 handles a specific task better, or a new model drops that excels at your use case, you can't route to it through Claude Code.

Chief's BYOA model lets you mix providers per task. Use Claude Code where Opus shines — complex refactors, nuanced architectural decisions — and Codex where GPT-5.5 excels. Chief manages both from a single interface, routing the right agent to the right milestone. You're never locked into one provider's strengths and weaknesses.

5. Team-wide visibility

Agent Teams is experimental, disabled by default, and limited to session-level coordination within a single codebase. There's no built-in system for coordinating which team member's Claude Code works on what or preventing duplicate agent work across a team.

Chief provides team-wide visibility into agent activity with shared projects and role-based access. Everyone sees what's in flight, what's completed, and what's queued — across all team members and projects from one dashboard.

6. Quality gates between agent output and merge

Claude Code can submit PRs, and Ultrareview provides general-purpose code review. But there's no built-in system for reviewing agent output against project-specific acceptance criteria before it ships.

Chief reviews every completed milestone against its acceptance criteria before marking it done. At scale — five projects, multiple agents — this is the difference between drowning in PRs and having a managed review pipeline.

When to add Chief

Add Chief to your Claude Code workflow when:

• You want to scale across projects. Chief lets you run agents across your entire portfolio from one dashboard — not five terminal sessions.
• You want one-shot execution of complex goals. Give Chief a goal, approve the plan, and it executes the full milestone sequence without you managing each step.
• You want proactive management. Chief figures out what to work on next based on project state — you stop being the bottleneck between tasks.
• You want to mix providers. Route Claude Code and Codex to the tasks each handles best, managed from a single interface.
• You work in a team. Unified visibility shows what every agent is doing.
• You want quality gates at scale. Chief reviews agent output against acceptance criteria before it hits your inbox.

Chief doesn't replace Claude Code — it turns every Claude Code session into part of a managed, portfolio-wide operation.

Getting started in 5 minutes

Already using Claude Code? Adding Chief takes minutes.

1. Sign up for Chief — free trial, no credit card.
2. Connect your Claude Code subscription — Chief uses your existing Anthropic account via BYOA. No new agent costs.
3. Import a project — give Chief a GitHub repo URL. It builds context automatically.
4. Set a goal — "add dark mode support" or "implement the billing page" or whatever's next.
5. Approve the plan — Chief proposes milestones with acceptance criteria. Review, adjust, approve.
6. Watch it execute — Chief dispatches Claude Code with the right context, executes the full plan, and reviews the output.

That's it. You're still using Claude Code — just with a manager running the show.

FAQ

Is Chief a replacement for Claude Code?

No. Chief manages Claude Code; it doesn't replace it. Claude Code does the coding. Chief does the planning, dispatching, and reviewing. You need both — Chief is the manager, Claude Code is the engineer.

Do I need a separate Claude Code subscription to use Chief?

You bring your existing Claude Code subscription. Chief uses a BYOA model — there's no additional agent cost from Chief.

Can Chief manage Claude Code alongside other agents?

Yes. Chief's BYOA model supports multiple agents. Use Claude Code for some tasks and Codex for others — Chief dispatches the right agent for each milestone from a single interface. That's the point: mix and match the best provider for each job.

How does Chief decide what to work on next?

Chief maintains persistent project context — completed milestones, in-flight work, project goals, codebase state. It uses this context to proactively propose the next milestones. You approve or redirect; Chief drives the pace.

What does "one-shot execution" actually mean?

You give Chief a complex goal — "add team billing with Stripe, usage metering, and an admin dashboard." Chief decomposes it into dependency-aware milestones, sequences them, and executes the entire plan. Each milestone is reviewed against acceptance criteria before the next begins. You approve once at the plan level, not at every step.

Can I still use Claude Code directly for hands-on work?

Absolutely. Chief manages background agent work — it doesn't take over your terminal. Use Claude Code interactively anytime, and use Chief for the work you want to delegate.

Claude Code has Agent Teams, Routines, and Ultraplan — doesn't that overlap?

These features extend Claude Code in important ways, but they operate at a different level. Agent Teams is experimental and session-scoped. Routines run on fixed schedules, not project-level goals. Ultraplan helps plan within a session but doesn't persist across sessions. Chief provides persistent project management, cross-project coordination, multi-provider dispatch, and proactive planning that sits above these features.

Does Chief work with any IDE?

Chief is IDE-agnostic. It dispatches coding agents in the background — your editor choice doesn't affect Chief.