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 atstaeff/ai-agents --skill agent-routinggit clone --depth 1 https://github.com/atstaeff/ai-agentsWrote 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/atstaeff/ai-agents/agent-routing)<a href="https://agentmods.dev/skills/atstaeff/ai-agents/agent-routing"><img src="https://agentmods.dev/badge/skills/atstaeff/ai-agents/agent-routing/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/atstaeff/ai-agents/agent-routing"><img src="https://agentmods.dev/badge/skills/atstaeff/ai-agents/agent-routing.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 | $0.00024 | $0.00408 |
| Opus 5.5 | $0.00010 | $0.00163 |
| Sonnet 5.5 | $0.00005 | $0.00082 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
agent-routing 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.
What it actually says
Agent Routing
- Handle clear, small tasks directly. When routing helps, reuse available metadata and inspect only what is missing. Load selected skill bodies.
- Use the narrowest relevant expertise: second-brain for PARA, product-manager for product uncertainty and domain experts for implementation. Skills can guide the current session without switching agents.
- Check actual host capabilities and instructions. Delegate only when tools exist, authorization permits it and the benefit exceeds coordination cost. Otherwise apply specialist guidance in the current session.
- Supply a bounded goal, context pointers, acceptance criteria, allowed files and expected evidence. Avoid concurrent writers to the same file.
- Inspect returned changes and checks, resolve contradictions and update an existing work record when present. A successful tool call does not prove completion.
Selection examples
| Outcome | Agent | Initial skills |
|---|---|---|
| Add a Python API endpoint | python-expert | python-patterns, api-design |
| Improve an interface | frontend-expert | frontend-patterns |
| Clarify a product increment | product-manager | product-discovery |
| File notes in a private vault | second-brain | obsidian-para |
| Coordinate several deliverables | joerg | work-management, agent-routing |
| Review a risky change | code-reviewer | code-review |
Host boundaries
- Exported profiles do not themselves create sessions. OpenCode's available native task/subagent tools determine delegation behavior.
- Do not promise that the user can type into a child session in every OpenCode Web release. Session visibility and interaction depend on the host UI.
- Do not invent tool names, models, account access or background execution. Select models by available capabilities and workload, not a hardcoded obsolete price table.
- Honor host permissions. A read-only reviewer must not become a writer merely because its Markdown describes a repair.
What ships with it
1 file 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.
- 11d ago Changed e4b0a8d9b5b6
- 12d ago First seen · 31 lines · 24 tokens per session scan A 713c337032a7
agent-routing is a skill published in the GitHub repository atstaeff/ai-agents (3 stars, last pushed 10d ago), licensed MIT. It adds 24 tokens to every session and 408 once invoked, about $0.0001 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 2026-10-08.
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…
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…