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 MerkyorLynn/Lynn --skill task-model-routergit clone --depth 1 https://github.com/MerkyorLynn/LynnWrote 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/merkyorlynn/lynn/task-model-router)<a href="https://agentmods.dev/skills/merkyorlynn/lynn/task-model-router"><img src="https://agentmods.dev/badge/skills/merkyorlynn/lynn/task-model-router.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00110 | $0.02426 |
| Opus 5 | $0.00055 | $0.01213 |
| Sonnet 5 | $0.00022 | $0.00485 |
| Haiku 4.5 | $0.00011 | $0.00243 |
Grade A, and why
task-model-router 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 8d 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task-Aware Model Router — Right Model for Every Task
Stop using one model for everything. Route chat to fast models, code to reasoning models, images to vision models, long docs to large-context models — automatically.
Part of Lynn — a personal AI agent where this routing is built into the core engine. Install Lynn to get task-aware routing out of the box, plus memory, IM bridge, and file protection.
Why One Model Isn't Enough
| Task | What You Need | What Happens With One Model |
|---|---|---|
| "Hey, what's up?" | Fast, cheap, 0.5s reply | Waste $0.03 on GPT-4 for a greeting |
| "Refactor this 500-line module" | Strong reasoning, tool use | Cheap model hallucinates, breaks code |
| "What's in this screenshot?" | Vision encoder | Text model ignores the image entirely |
| "Summarize this 80-page PDF" | 128k+ context window | Small model truncates, loses key info |
One model = overpaying for simple tasks, underpowering hard tasks.
The Strategy: Task Classification → Model Selection
Incoming message
↓
┌─ Classify Task ─────────────────────────────┐
│ │
│ has images? ──→ VISION model │
│ code keywords? ──→ REASONING model │
│ long input (>8k)? ──→ LARGE CONTEXT │
│ else ──→ FAST model │
└───────────────────────────────────────────────┘
↓
Selected model handles the request
↓
If selected model fails → fallback to next best
Task Detection Rules
Rule 1: Vision (Image Understanding)
Trigger: Message contains image content blocks, or user says "look at this", "what's in this photo", "describe this screenshot"
function needsVision(messages) {
const last = messages[messages.length - 1];
if (Array.isArray(last.content)) {
return last.content.some(b => b.type === 'image');
}
return false;
}
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.
- 8d ago First seen · 247 lines · 110 tokens per session scan A 09c7376e4bc7
task-model-router is a skill published in the GitHub repository MerkyorLynn/Lynn (42 stars, last pushed yesterday), licensed Apache-2.0. It adds 110 tokens to every session and 2,426 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
ai-prompt-optimizer
Optimize prompts for better LLM responses. Use when users want to improve prompt clarity, add structure, enhance specificity, or need prompt templates for specific tasks. Uses CodeAgent for analysis and generation, and MemoryAgent for storing optimized prompts.
cua-driver
Drive a native GUI app (macOS, Windows, Linux) via the Qwen Cua Driver CLI (default) or MCP server; snapshot its accessibility tree, act through snapshot-bound element tokens, native menu paths, exact window geometry, or pixel coordinates, and verify from fresh state. Use when the user asks you to operate, drive…
codegraph
Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
e2e-testing
Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response…
structured-debugging
Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…