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 agents/yogasw/wick/airoutergit clone --depth 1 https://github.com/yogasw/wickWhat 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 | $0.00000 | $0.01761 |
| Opus 5 | $0.00000 | $0.00881 |
| Sonnet 5 | $0.00000 | $0.00352 |
| Haiku 4.5 | $0.00000 | $0.00176 |
Grade A, and why
airouter 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 2d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Router
AI Router embeds one or more local LLM router/proxy dashboards inside wick — accessible with no shell access and no exposed port. Today it ships two backends you can run side by side and switch between:
- 9router — an LLM router + proxy dashboard.
- OmniRoute — an AI gateway that aggregates many providers behind one OpenAI-compatible endpoint.
Wick installs, manages, and reverse-proxies each one. Every router is reachable through the same wick URL with no extra tunnel or firewall rule. More routers can be added over time, and each provider instance can be pointed at whichever router you choose.
Where to find it
Go to Agents → More → AI Router in the sidebar (/tools/agents/airouter). The page is admin-only — non-admin users do not see the entry.
Switching routers
When more than one router is registered, a switcher row at the top of the page lists each one with a live status dot. Click a router to view its Dashboard, Requests, and Settings. Routers run concurrently — each on its own loopback port — so you can start several and flip between them to compare or check any of them without stopping the others.
Each router is proxied under its own prefix at the wick root: /airouter/9router/, /airouter/omniroute/, and so on.
Dashboard tab
The Dashboard tab embeds the selected router's web UI in an iframe. It behaves like the standalone dashboard — configure routes, inspect logs, manage keys — without leaving wick. The iframe follows wick's active light/dark theme automatically.
Requests tab
The Requests tab is a live stream of the calls proxied through the selected router's /airouter/<id>/v1 API. Bodies are captured only while the tab is open and held in your browser — nothing is stored on the server.
Settings tab
The Settings tab manages the selected router's process.
Install / Update
Each router is an npm package (9router, omniroute, …). Wick installs it on demand — npm must be on the host PATH.
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.
- 2d ago First seen · 133 lines · 0 tokens per session scan A 333d5de82c86
airouter is an agent published in the GitHub repository yogasw/wick (5 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,761 tokens. 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 agents, from other repositories
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
context
You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
task-plan-architect
Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
platform-engineer
Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.