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/kissrosecicd-hub/agents-evolution/multi-session-workernpx skills add kissrosecicd-hub/agents-evolution --skill multi-session-workergit clone --depth 1 https://github.com/kissrosecicd-hub/agents-evolutionWrote 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/kissrosecicd-hub/agents-evolution/multi-session-worker)<a href="https://agentmods.dev/skills/kissrosecicd-hub/agents-evolution/multi-session-worker"><img src="https://agentmods.dev/badge/skills/kissrosecicd-hub/agents-evolution/multi-session-worker.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 | $0.00078 | $0.02049 |
| Opus 5 | $0.00039 | $0.01025 |
| Sonnet 5 | $0.00016 | $0.00410 |
| Haiku 4.5 | $0.00008 | $0.00205 |
Grade C, and why
meta-multi-session-worker scanned grade C with 1 finding 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 5d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .workers/ How it starts
The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta: Multi-Session Workers
Оркестрация воркеров в отдельныхых tmux-сессиях — когда in-session subagents (Agent tool) недостаточно.
Чем отличается от in-session subagents
| In-session subagents | Multi-session workers | |
|---|---|---|
| Механизм | Agent tool внутри одной LLM сессии |
Отдельные CLI-процессы в tmux |
| Контекст | Общий, ограниченный | Изолированный у каждого |
| Лимит | ~4 параллельно | Сколько хватит CPU/памяти |
| Сбой одного | Загрязняет общий контекст | Полностью изолирован |
| Общение | Return values | Файлы + tmux capture |
| Когда использовать | Быстрые задачи, аудит | Тяжёлые задачи, генерация кода, тесты |
Архитектура
┌─────────────────────────────────────┐
│ Main Agent (текущая сессия Qwen) │
│ ┌───────────────────────────────┐ │
│ │ Координация: │ │
│ │ 1. Раздача задач │ │
│ │ 2. Мониторинг статуса │ │
│ │ 3. Сбор результатов │ │
│ │ 4. Synthesis │ │
│ └───────────────────────────────┘ │
└──────────┬──────────────┬───────────┘
│ │
┌──────▼──────┐ ┌─────▼──────┐
│ tmux: w-0 │ │ tmux: w-1 │
│ qwen code │ │ codex │
│ "audit code"│ │ "write tests"│
└─────────────┘ └────────────┘
│ │
┌──────▼──────────────▼──────┐
│ .workers/ │
│ ├── tasks/ │
│ │ ├── task-0.json │
│ │ └── task-1.json │
│ ├── results/ │
│ │ ├── result-0.md │
│ │ └── result-1.md │
│ └── status.json │
└─────────────────────────────┘
Протокол задач
Формат задачи: .workers/tasks/task-N.json
{
"id": "task-0",
"worker": "worker-0",
"cli": "qwen",
"task": "Проведи полный аудит безопасности /home/qwen/kanban-board/. Проверь: секреты, инъекции, XSS, CORS, auth. Отчёт на русском.",
"context_file": ".workers/context/project-overview.md",
"expected_output": "security-report.md",
"status": "pending",
"created_at": "2026-04-07T12:00:00Z"
}
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.
- 5d ago First seen · 225 lines · 78 tokens per session scan C 8acc40ad06ae
meta-multi-session-worker is a skill published in the GitHub repository kissrosecicd-hub/agents-evolution (31 stars, last pushed 4mo ago), licensed MIT. It adds 78 tokens to every session and 2,049 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…