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 peteromallet/Arnold --skill subagent-launchergit clone --depth 1 https://github.com/peteromallet/ArnoldWrote 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/peteromallet/arnold/subagent-launcher)<a href="https://agentmods.dev/skills/peteromallet/arnold/subagent-launcher"><img src="https://agentmods.dev/badge/skills/peteromallet/arnold/subagent-launcher/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/peteromallet/arnold/subagent-launcher"><img src="https://agentmods.dev/badge/skills/peteromallet/arnold/subagent-launcher.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 | $0.00121 | $0.05245 |
| Opus 5.5 | $0.00048 | $0.02098 |
| Sonnet 5.5 | $0.00024 | $0.01049 |
| Haiku 4.5 | $0.00012 | $0.00524 |
Grade A, and why
subagent-launcher 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 1mo 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Subagent launcher (multi-model)
Dispatch work to a model other than the one driving the conversation. Two payoffs: independence — a different model's judgement, not a copy of your own — and context hygiene — the subagent's tool calls and reasoning stay in its context; only the conclusion returns to you.
Pathways:
| Pathway | Model | Invocation | Tools |
|---|---|---|---|
| omp agentic (default) | DeepSeek V4 (Pro/Flash), Kimi K2.7, Zhipu GLM, … | launch_omp_agent.py — or fan.py to run N in one process |
file, web, optional terminal |
| Codex | GPT-5.5 | codex exec (CLI) |
sandboxed workspace |
| Claude | Claude (Opus/Sonnet/Haiku) | launch_claude_agent.py --model=opus or Claude Code Agent tool |
Claude Code tools |
| Grok via omp | Grok 4.6 / 4.5 | launch_omp_agent.py --model=grok-4.6 |
full omp toolset (Bash, Read, Edit, …) |
Default to the omp agentic pathway, and to DeepSeek Flash within it — different model family, cheap, fast, tool-using. Reach for DeepSeek Pro only when the task needs reasoning judgement; reach for Codex or Claude only when you specifically want their strengths.
⚠️ Network sandbox warning for Codex subagents
codex execruns its subprocess withCODEX_SANDBOX_NETWORK_DISABLED=1. omp agents (DeepSeek/Kimi/MiMo/GLM/OpenRouter) need outbound network to reach their provider APIs, so launching them from inside acodex execsubagent will fail. The launcher itself is fine; it fails only because the parent process has no network.Workarounds:
Launch the omp subagent directly from a normal shell or Bash tool.
If you need a Codex subagent to orchestrate omp subagents, run the outer Codex command with
--sandbox danger-full-accessand seal stdin with</dev/null, for example:timeout 3600 codex exec --sandbox danger-full-access \ -c model_reasoning_effort=high \ "$(cat /tmp/brief.md)" </dev/null
read-onlyandworkspace-writeboth disable outbound network for the Codex subprocess; onlydanger-full-accessallows nested omp provider API calls from insidecodex exec. Tell Codex explicitly to uselaunch_omp_agent.pyorfan.py, and to spend its own context budget by delegating broad searches, file mapping, and independent reviews to DeepSeek/Kimi subagents wherever practical.This network restriction does not affect Codex or Claude subagents.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 282 lines · 121 tokens per session scan A 7242a175a185
subagent-launcher is a skill published in the GitHub repository peteromallet/Arnold (98 stars, last pushed yesterday), licensed Apache-2.0. It adds 121 tokens to every session and 5,245 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…