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 mekotenkov-ux/seomeatagentscreator --skill subagent-orchestratorgit clone --depth 1 https://github.com/mekotenkov-ux/seomeatagentscreatorWrote 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/mekotenkov-ux/seomeatagentscreator/subagent-orchestrator)<a href="https://agentmods.dev/skills/mekotenkov-ux/seomeatagentscreator/subagent-orchestrator"><img src="https://agentmods.dev/badge/skills/mekotenkov-ux/seomeatagentscreator/subagent-orchestrator/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/mekotenkov-ux/seomeatagentscreator/subagent-orchestrator"><img src="https://agentmods.dev/badge/skills/mekotenkov-ux/seomeatagentscreator/subagent-orchestrator.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 | $0.00066 | $0.00581 |
| Opus 5 | $0.00033 | $0.00291 |
| Sonnet 5 | $0.00013 | $0.00116 |
| Haiku 4.5 | $0.00007 | $0.00058 |
Grade A, and why
subagent-orchestrator 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 11d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent Orchestrator
Subagents нужны для ограниченной независимой работы. Они не являются автоматическим усилителем качества.
Перед запуском
- Прочитайте
../../references/subagent-orchestration.md. - Подтвердите authorization: прямой запрос пользователя, применимый workflow/skill contract или platform policy.
- Оцените decomposability, dependencies, tool density, context value, write overlap, verification и economics.
- Если single agent надежнее или дешевле, запишите
single_agentи не делегируйте.
Порядок работы
- Выберите topology:
single_agent|agent_as_tool|handoff|sequential_chain|parallel_fanout|critic_loop|agent_team|batch_map. - Заполните role registry и delegation plan.
- Создайте один task contract на worker с disjoint ownership и expected result schema.
- Передайте compact context pack. Fresh context - default; fork разрешен только когда benefit и privacy cost записаны.
- Запускайте только независимые sidecar tasks параллельно. Immediate blocking work оставляйте parent.
- Не используйте параллельные writes в одном mutable checkout. Выделите worktree/container или disjoint resource scope.
- Следите за lifecycle, budgets, approvals, cancellation и completed thread cleanup.
- Требуйте structured result и artifact/evidence refs. Partial/failed/timed-out task тоже обязан вернуть запись.
- Parent проверяет counts, artifacts и disagreements, затем синтезирует. Worker narrative не является evidence.
- Запустите Subagent Eval Lab и сравните с single-agent baseline.
Ограничения
- Default max depth: 1.
- Не создавайте workers только потому, что доступен concurrency slot.
- Не давайте subagent больше permissions, чем parent и task требуют.
- Не разрешайте background worker обходить approval.
- Не передавайте reviewer intended fix или hidden desired verdict.
- Не логируйте raw transcript, secrets и credentials.
- Agent team/peer messaging требует отдельного обоснования и пометки experimental, если target так его классифицирует.
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.
- 11d ago First seen · 43 lines · 66 tokens per session scan A 80153552248f
subagent-orchestrator is a skill published in the GitHub repository mekotenkov-ux/seomeatagentscreator (5 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 581 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…