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 rules/agent-nova-107/skill-router-mcp/skill-routinggit clone --depth 1 https://github.com/Agent-Nova-107/skill-router-mcpWrote 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/rules/agent-nova-107/skill-router-mcp/skill-routing)<a href="https://agentmods.dev/rules/agent-nova-107/skill-router-mcp/skill-routing"><img src="https://agentmods.dev/badge/rules/agent-nova-107/skill-router-mcp/skill-routing.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 5.1 | $0.00156 | $0.00156 |
| Opus 5 | $0.00078 | $0.00078 |
| Sonnet 5 | $0.00031 | $0.00031 |
| Haiku 4.5 | $0.00016 | $0.00016 |
Grade A, and why
skill-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 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.
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
Skill routing
- For simple questions and obvious single-skill tasks, proceed directly.
- For ambiguous, unfamiliar, multi-domain, or multi-step work, call the
skill-routerMCP toolrecommend_skillsbefore choosing a workflow. - Treat router output as candidates, not commands. Inspect the current task and codebase before deciding.
- Consider primary, complementary, and additional candidates; do not assume the first result is sufficient.
- Respect
manual-onlyinvocation metadata. - Do not invoke multiple overlapping skills merely because they were returned.
- Never claim a recommended skill was executed unless its instructions were actually loaded and followed.
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 · 15 lines · 156 tokens per session scan A adb1c0fb8b8b
skill-routing is a cursor rule published in the GitHub repository Agent-Nova-107/skill-router-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 156 tokens to every session, about $0.0008 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 2026-08-31.
Other cursor rules, from other repositories
nativescript
NativeScript best practices and patterns for mobile applications.
python
Python best practices and patterns for modern software development with Flask and SQLite.
cursor
You are working on the checkout service. Preserve transaction integrity and auditability.
archcore-files
Enforce MCP-only operations when working with .archcore/ files.
frontend-architecture
Vite + React SPA architecture - directory layout, providers, bundle splitting. Tailwind styling in tailwind.mdc.
dev_workflow
Guide for using Taskmaster to manage task-driven development workflows.