Quick Start

Once you’ve installed the plugin, the orchestrator skill and native system-prompt contribution are loaded automatically in every session - no extra commands, no manual setup.

The orchestrator is not always the fastest path

Kimi Code can dispatch several subagents, but every dispatch adds model work and waiting time. Use the usage decision guide before routing a small task or an expensive model through the full pipeline.

What to expect

Launch Kimi Code as usual. At session start, the orchestrator skill auto-loads via sessionStart.skill in kimi.plugin.json. You’ll see a plugin session-start block referencing the orchestrator’s methodology, and the plugin’s SYSTEM.md contribution is loaded through systemPromptPath.

The orchestrator is the routing layer. It does not implement, debug, or edit code itself - it loads specialist skills via the Skill tool and dispatches them to Kimi Code’s 3 built-in subagents (coder, explore, plan).

Try a single delegation

Hand a concrete, scoped task to the builder persona (dispatched to the coder subagent):

“Use builder to add a JSDoc comment to the add function in src/math.ts.”

The orchestrator loads the builder SKILL.md, inlines the persona into an Agent call, and dispatches to the coder subagent. The coder subagent has Write/Edit/Bash access by default.

Try a multi-step task

For work that spans multiple specialists, hand the whole thing to the orchestrator:

“The login flow throws on empty email. Trace the bug, fix it, and review the fix.”

The orchestrator decomposes the work:

1. diagnose (coder) - 6-step root cause trace
2. builder (coder) - apply the minimal fix
3. reviewer (coder; no-edit only in a review-only session with Write/Edit denied) - validate the fix

Each step verifies before handing off to the next.

Try swarm fan-out

For ≥3 uniform items, the orchestrator uses AgentSwarm:

“Review these 5 files for security issues: src/auth.ts, src/api.ts, src/db.ts, src/routes.ts, src/middleware.ts.”

The orchestrator:

1. Identifies ≥3 uniform independent items.
2. Loads the reviewer persona.
3. Calls AgentSwarm with a prompt_template that includes the reviewer persona + {{item}} placeholder.
4. Returns a single <agent_swarm_result> envelope with one <subagent> per file.

AgentSwarm must be the only tool call in the turn (exclusive-deny policy) - no “explore first, then swarm” in one turn.

Try a multi-phase plan

For complex features, get a phased plan from planner (dispatched to the plan subagent) before implementing:

“Use planner to draft a migration plan from REST to GraphQL.”

The planner persona returns phases with success criteria and rollback points. Hand the plan to the orchestrator for execution, or to builder for individual phases.

Common pitfalls

• Plugin not enabled - run /plugins list and /plugins info maestria; then /plugins reload or /new.
• Forgot [[hooks]] - destructive bash commands (rm -rf) slip through. Save the companion script as ~/.kimi-code/hooks/block-dangerous-bash.mjs.
• Forgot [[permission.rules]] - the reviewer persona can edit files because the coder subagent has Write/Edit tools. Persona text alone is advisory, not enforcement.
• Skipped /new - plugin changes don’t take effect in the current session. Run /reload then /new.
• Orchestrator starts writing code directly - the orchestrator skill is supposed to route, not implement. Check /plugins list and confirm the session-start skill loaded.
• AgentSwarm not available - use Kimi Code v0.38.0+; older releases are outside the verified support boundary.

Native workflow commands

Kimi namespaces commands contributed by plugins. Use /maestria:fein, /maestria:sonar, or /maestria:blitz when you want an explicit route.

Pipeline reference

The full pipeline diagram is in Workflow Patterns.

Tip

Choose the smallest safe route. Use direct execution for known, low-risk work when the host permits it; use recon (adventurer) or design (architect) when the code is unfamiliar or the approach is uncertain. The orchestrator handles this routing automatically - but you can also invoke specialists directly when you know which one you want.

Next Steps

• Skill Reference - Full reference for all 8 skills
• Workflow Patterns - Practical examples for each skill