orchestrate

A command for coordinating at least three specialised agents on one complex task, such as a review or investigation.

In plain words
What is it for?
Use it for multi-perspective analysis, comprehensive reviews, or work that needs several areas of technical expertise.
Why use it?
It separates a large problem into different expert viewpoints and requires enough agents to cover it properly.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/felipeslo/opencode-kit/orchestrate
Clone the repo
git clone --depth 1 https://github.com/felipeslo/opencode-kit
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,843 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.01843
Opus 5 $0.00012 $0.00922
Sonnet 5 $0.00005 $0.00369
Haiku 4.5 $0.00002 $0.00184

Measured yesterday against content hash eb9849737b89, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchestrate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.opencode/commands/orchestrate.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Agent Orchestration

You are now in ORCHESTRATION MODE. Your task: coordinate specialized agents to solve this complex problem.

Task to Orchestrate

$ARGUMENTS


🔴 CRITICAL: Minimum Agent Requirement

⚠️ ORCHESTRATION = MINIMUM 3 DIFFERENT AGENTS

If you use fewer than 3 agents, you are NOT orchestrating - you're just delegating.

Validation before completion:

  • Count invoked agents
  • If agent_count < 3 → STOP and invoke more agents
  • Single agent = FAILURE of orchestration

Agent Selection Matrix

Task Type REQUIRED Agents (minimum)
Web App frontend-specialist, backend-specialist, test-engineer
API backend-specialist, security-auditor, test-engineer
UI/Design frontend-specialist, seo-specialist, performance-optimizer
Database database-architect, backend-specialist, security-auditor
Full Stack project-planner, frontend-specialist, backend-specialist, devops-engineer
Debug debugger, explorer-agent, test-engineer
Security security-auditor, penetration-tester, devops-engineer

Pre-Flight: Mode Check

Current Mode Task Type Action
plan Any ✅ Proceed with planning-first approach
edit Simple execution ✅ Proceed directly
edit Complex/multi-file ⚠️ Ask: "This task requires planning. Switch to plan mode?"
ask Any ⚠️ Ask: "Ready to orchestrate. Switch to edit or plan mode?"

🔴 STRICT 2-PHASE ORCHESTRATION

PHASE 1: PLANNING (Sequential - NO parallel agents)

Step Agent Action
1 project-planner Create docs/PLAN.md
2 (optional) explorer-agent Codebase discovery if needed

🔴 NO OTHER AGENTS during planning! Only project-planner and explorer-agent.

⏸️ CHECKPOINT: User Approval

After PLAN.md is complete, ASK:

"✅ Plan created: docs/PLAN.md

Do you approve? (Y/N)
- Y: Start implementation
- N: I'll revise the plan"

Read the full file on GitHub · 238 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 238 lines · 24 tokens per session scan A eb9849737b89

Subscribe to this mod's changes

orchestrate is a command published in the GitHub repository felipeslo/opencode-kit (2 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 1,843 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.