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.
npx skills add VoDaiLocz/kilo-kit-mcp --skill multi-agent-orchestrationgit clone --depth 1 https://github.com/VoDaiLocz/kilo-kit-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/multi-agent-orchestration)<a href="https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/multi-agent-orchestration"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/multi-agent-orchestration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/multi-agent-orchestration"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/multi-agent-orchestration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.00982 |
| Opus 5 | $0.00020 | $0.00491 |
| Sonnet 5 | $0.00008 | $0.00196 |
| Haiku 4.5 | $0.00004 | $0.00098 |
Grade A, and why
multi-agent-orchestration 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 2d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Agent Orchestration
Overview
This skill provides a framework for designing and managing multi-agent systems where specialized agents collaborate on complex, multi-stage workflows. It emphasizes clear agent boundaries, structured communication, and robust error isolation.
When To Use
- When tasks are too large or diverse for a single agent (scope creep).
- When specific domain expertise (e.g., database design, UI/UX, security) is required in separate, modular contexts.
- To maintain clean separation of concerns and reduce context window degradation.
- When you need to delegate parallelizable work to maximize throughput.
Topology Patterns
- Hierarchical Supervisor: A central supervisor agent delegates sub-tasks to specialized workers, aggregates their results, and provides final synthesis.
- Swarm Handoffs: Agents pass tasks directly to the next appropriate agent based on completion criteria, forming a chain or graph of expertise.
- Router-Worker: A router analyzes incoming requests and dispatches them to a specific pool of workers based on classification.
- Blackboard: Multiple agents read from and write to a shared persistent state (the "blackboard") until a task objective is satisfied.
- Round-Robin Debate: Agents with opposing viewpoints propose solutions, iterate, and refine based on peer criticism to improve quality.
Communication Protocols
- Agent-to-Agent (A2A): Always use structured message framing.
- Structured Payloads: Encapsulate tasks, constraints, and dependencies in a common JSON format or structured Markdown.
- Return Summaries: Every subagent MUST return a concise summary of work done, resources created, and final status (SUCCESS/FAIL/BLOCKED) before closing the conversation.
Context Isolation & Boundary Hand-offs
- Ephemeral Context: Spawn subagents with only the minimal, high-signal information needed for their specific task.
- Avoid Token Bloat: Do not pass the entire parent conversation history unless strictly necessary. Pass pointers to file locations or artifact links instead.
- Clean State: Each subagent should operate within its own branched workspace to prevent side effects on the parent or other subagents.
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.
- 2d ago Changed scan B → A 2cc06c76bca3
- 10d ago First seen · 65 lines · 40 tokens per session scan B c65e95b84487
multi-agent-orchestration is a skill published in the GitHub repository VoDaiLocz/kilo-kit-mcp (26 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 982 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
llm-structured-output
Get reliable JSON, enums, and typed objects from LLMs using responseformat, tooluse, and schema-constrained decoding across OpenAI, Anthropic, and Google APIs.
drizzle-orm-expert
Expert in Drizzle ORM for TypeScript — schema design, relational queries, migrations, and serverless database integration. Use when building type-safe database layers with Drizzle.
landing-page-generator
Generates high-converting Next.js/React landing pages with Tailwind CSS. Uses PAS, AIDA, and BAB frameworks for optimized copy/components (Heroes, Features, Pricing). Focuses on Core Web Vitals/SEO.
tdmcp-pipeline
Orchestrates the tdmcp feature team end-to-end: design/wireframe → build → integrate → QA → release. Use whenever the user wants to build, implement, develop, ship, or add one or more tdmcp features/tools/effects/controls/AI-prompts for TouchDesigner, or to run them through a coordinated design→develop→QA→deploy…
memb-skill
BDB local-first long-term memory engine (memB). Use when querying, remembering, or adapting preferences, code architectures, and developer patterns across tasks.
startcycle-graph-user
Use when a task needs a small, throwaway multi-agent fan-out (a couple of parallel workers plus a review pass) in ANY project, without the full /startcycle-graph contract — no .agents/graph.md bootstrap, no state.json schema, no persistent files. Model-tiered by role (opus plan, sonnet review, haiku or an external CLI…