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 k9aif/k9-aif-framework --skill add-routergit clone --depth 1 https://github.com/k9aif/k9-aif-frameworkWrote 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/k9aif/k9-aif-framework/add-router)<a href="https://agentmods.dev/skills/k9aif/k9-aif-framework/add-router"><img src="https://agentmods.dev/badge/skills/k9aif/k9-aif-framework/add-router/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/k9aif/k9-aif-framework/add-router"><img src="https://agentmods.dev/badge/skills/k9aif/k9-aif-framework/add-router.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 | $0.00584 |
| Opus 5 | $0.00012 | $0.00292 |
| Sonnet 5 | $0.00005 | $0.00117 |
| Haiku 4.5 | $0.00002 | $0.00058 |
Grade A, and why
add-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 9d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before doing anything else, check that /k9aif:configure has been run.
If K9AIF_PROJECT_ROOT and K9AIF_APP_NAME are not set, refuse and say:
"Please run
/k9aif:configurefirst to set your project root and app name." Do not proceed until init has been run.
K9-AIF: Add Router
Scaffold a custom model router that replaces K9ModelRouter. Use this when a solution needs custom routing logic — cost optimisation, compliance routing, A/B testing, or provider switching.
The user provides: <RouterName> <AppName> (e.g. ComplianceRouter MyApp).
When to use
Only create a custom router when K9ModelRouter is insufficient. If the catalog scoring (task_type, sensitivity, latency_budget, cost_profile) covers the use case, keep the OOB router and just update config.yaml.
What to generate
Python class — examples/<AppName>/routers/<router_name_lower>.py
from k9_aif_abb.k9_inference.routers.base_model_router import BaseModelRouter
from k9_aif_abb.k9_inference.models.inference_request import InferenceRequest
from k9_aif_abb.k9_inference.models.route_decision import RouteDecision
class <RouterName>(BaseModelRouter):
def route(self, request: InferenceRequest) -> RouteDecision:
# Custom routing logic — pick a model alias from the catalog
alias = "reasoning" if request.task_type == "reasoning" else "general"
return RouteDecision(model_alias=alias)
def invoke(self, request: InferenceRequest):
decision = self.route(request)
llm = self._get_llm(decision.model_alias)
return llm.invoke(request.prompt)
Register in config.yaml
inference:
router:
type: <router_name_lower>
default_model: general
persistence:
enabled: true
provider: sqlite
Rules to follow
- Extend
BaseModelRouter, notK9ModelRouter. route()must return aRouteDecisionwith a validmodel_aliasfrom the catalog.- Use
self._get_llm(alias)(inherited) to get theOllamaLLMinstance — never instantiate LLMs directly. - Register the router type string in config to match the class file name (convention, not enforced).
- Agents, squads, and orchestrators are unaffected by router substitution — routing is fully decoupled.
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.
- 9d ago First seen · 62 lines · 24 tokens per session scan A c09ecc80cfef
add-router is a skill published in the GitHub repository k9aif/k9-aif-framework (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 24 tokens to every session and 584 once invoked, about $0.0001 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…