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 agentmods add skills/hoja-solutions/agent-stdlib/multi-agent-orchestrationnpx skills add Hoja-Solutions/agent-stdlib --skill multi-agent-orchestrationgit clone --depth 1 https://github.com/Hoja-Solutions/agent-stdlibWrote 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/hoja-solutions/agent-stdlib/multi-agent-orchestration)<a href="https://agentmods.dev/skills/hoja-solutions/agent-stdlib/multi-agent-orchestration"><img src="https://agentmods.dev/badge/skills/hoja-solutions/agent-stdlib/multi-agent-orchestration.svg" alt="Measured on agentmods" 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 | $0.00160 | $0.00831 |
| Opus 5 | $0.00080 | $0.00415 |
| Sonnet 5 | $0.00032 | $0.00166 |
| Haiku 4.5 | $0.00016 | $0.00083 |
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 3d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-agent orchestration
Source: How we built our multi-agent research system. The pattern lives in Anthropic's cookbook as notebooks and prompts. This packages the parallel-research recipe as a skill, with the judgment of when to use it. The pack also ships a /research command and a research-worker subagent that run this flow.
A lead agent plans a question, spawns several subagents to chase parts of it in parallel, and synthesizes what they return. Each subagent has its own context window, so the system explores far more ground than one agent could hold at once. That power has a price, so the first decision is whether to use it at all.
Use it for breadth, not for coupling
Multi-agent fits work that splits into independent pieces explored at the same time: surveying a literature, gathering evidence from many sources, mapping a large unknown space. It fits poorly when the pieces depend on each other.
Do not reach for it on a coding task with shared state, or anything that needs tight coordination between the parts, because the subagents cannot see each other's context and will step on the shared thing. A multi-agent run also costs on the order of 15 times the tokens of a single chat. Spend that only when the breadth is worth it.
Delegate so workers do not collide
A vague subagent prompt produces overlap and gaps. Give each worker four things:
- a specific objective, narrow enough that two workers will not duplicate it
- the output format you want back
- guidance on which tools to use
- explicit boundaries on what to leave to other workers
Scale the effort to the task. A simple question wants one agent and a handful of tool calls. A complex one warrants ten or more subagents. Stating the scale in the lead's plan stops it from over- or under-spawning.
Search broad, then narrow
Have agents open with broad queries to map the space, then tighten toward the specifics. Use extended or interleaved thinking in the lead for planning the decomposition and for judging what comes back, so the synthesis reacts to the findings rather than to the original plan.
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.
- 3d ago First seen · 56 lines · 160 tokens per session scan A a8a84fedd0b1
multi-agent-orchestration is a skill published in the GitHub repository Hoja-Solutions/agent-stdlib (1 stars, last pushed 1mo ago), licensed MIT. It adds 160 tokens to every session and 831 once invoked, about $0.0008 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.
Other skills, from other repositories
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…