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 jason21wc/ai-governance-mcp --skill model-routinggit clone --depth 1 https://github.com/jason21wc/ai-governance-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/skills/jason21wc/ai-governance-mcp/model-routing)<a href="https://agentmods.dev/skills/jason21wc/ai-governance-mcp/model-routing"><img src="https://agentmods.dev/badge/skills/jason21wc/ai-governance-mcp/model-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/jason21wc/ai-governance-mcp/model-routing"><img src="https://agentmods.dev/badge/skills/jason21wc/ai-governance-mcp/model-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 | $0.00095 | $0.01666 |
| Opus 5 | $0.00048 | $0.00833 |
| Sonnet 5 | $0.00019 | $0.00333 |
| Haiku 4.5 | $0.00010 | $0.00167 |
Grade A, and why
model-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 10d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/model-routing — Subagent Model & Effort Dispatch
Quick-reference for routing subagent model and effort via the Agent tool or Workflow scripts.
Context
Available models: sonnet, opus, haiku, fable — aliases that auto-resolve to the latest generation on each release. Check the system prompt ("You are powered by…") for the current resolution.
Effort: settable in Workflow agent(prompt, {effort: "high"}) only. The Agent tool has no effort parameter — subagents inherit session effort. Levels: low/medium/high/xhigh/max on opus, sonnet, and fable. haiku has no effort parameter — omit it there.
Default: omit model to inherit the session model. Only override when the task's cognitive function demands a different tier.
Core Principle
Effort is the primary lever; model is the ceiling. Raising effort on a cheaper model often outperforms dropping effort on a more expensive one. Route by cognitive function, not by generic "difficulty."
Routing Table
| Cognitive Function | Model | Effort | When to use |
|---|---|---|---|
| Heavy implementation | opus |
xhigh | Multi-file code changes, complex refactors, architectural rewrites |
| Deep analysis | opus |
high | Security audits, multi-file code review, architecture assessment |
| Hardest reasoning | fable |
high | Long-horizon autonomous runs, problems opus stalls on — 2× opus cost, so earn it |
| LLM-as-judge | fable |
medium | Eval scoring, independent quality assessment, grading rubrics |
| Standard tasks | sonnet |
medium | Single-file edits, test writing, documentation, data transforms |
| Mechanical work | sonnet |
low | Log analysis, formatting, simple lookups, template expansion |
| Fast classification | haiku |
omit | Categorization, boolean checks, format validation (no effort parameter; row is out of DOE #209 scope — untested) |
| Cross-vendor review | Codex (MCP) | n/a | Independent second opinion, peer review — dispatched via mcp__codex__codex, not Agent tool; effort param not exposed |
| Inherit (no override) | omit | omit | Task matches session model's tier — often the right call |
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.
- 10d ago First seen · 87 lines · 95 tokens per session scan A 06441e1c8b18
model-routing is a skill published in the GitHub repository jason21wc/ai-governance-mcp (0 stars, last pushed 10d ago), licensed Apache-2.0. It adds 95 tokens to every session and 1,666 once invoked, about $0.0005 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…