Kata Agent Team
Autonomous coding agents that continuously improve
An autonomous agent team that keeps getting better — organized as a daily Plan-Do-Study-Act cycle. Nineteen skills. A focused agent roster. Zero infrastructure.
Agent teams fail when they get complicated.
Most agent setups accumulate heavy infrastructure, sprawling toolchains, and prompt chains that nobody can audit. Kata takes the opposite path. It gives you what you need and nothing more.
One cycle. Every day.
Every workflow maps to a phase. Findings from Study always re-enter the loop. Every observation leads to downstream action.
Turn approved specs into architectural designs. Then turn the designs into executable plans with steps, files, sequence, and risks.
Execute plans through implementation PRs. Run scheduled workflows that harden, release, and maintain. Every run captures a trace.
Analyze outputs across four streams: security audits, feedback triage, documentation review, and grounded theory from traces.
Trivial findings become fix PRs. Structural findings become spec documents. Fix and spec branches never mix.
Eight agents. Explicit scope.
Each persona knows what it must do. It also knows what it must not do. When a finding exceeds scope, the agent writes a spec. It does not try the fix.
Owns the full spec, design, plan, implement arc for approved specs.
Keeps PR branches merge-ready, repairs CI, cuts releases. The sole external merge point.
Patches dependencies, hardens supply chain, enforces security policies.
Audits codebase health, reviews maintainability, and clears debt with no change to behavior.
Triages issues against product vision, reviews spec quality, runs evaluations.
Reviews docs for accuracy, curates agent memory, fixes staleness.
Retires stale logs, storyboards, and completed or cancelled specs once their signal is safely preserved.
Facilitates the daily storyboard meeting and 1-on-1 coaching sessions.
Same agents. Every surface.
Your IDE, a cron schedule, a GitHub event, or a bridged message triggers the same profiles and skills. They operate identically in each case.
One Git repo of markdown files.
Every agent reads and writes the same wiki: priorities, logs, metrics, and storyboards. A scheduled shift, a bridge-dispatched message, and an IDE session all share the same state. No database. Markdown files in a Git repository.
Set up the team in three lines.
Install the skill pack. Tell Claude to set up the team.
Take the full path in Get started, then read the documentation.