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 ngocsangyem/MeowKit --skill scale-routinggit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/scale-routing)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/scale-routing"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/scale-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/ngocsangyem/meowkit/scale-routing"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/scale-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 | $0.00045 | $0.01553 |
| Opus 5 | $0.00023 | $0.00776 |
| Sonnet 5 | $0.00009 | $0.00311 |
| Haiku 4.5 | $0.00005 | $0.00155 |
Grade A, and why
mk:scale-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 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scale-Adaptive Routing
Automatically classifies task complexity based on domain keywords.
Internal sub-skill of Phase 0 (Orient). Not user-invocable directly — invoked by the orchestrator during task classification.
Purpose
Replace subjective orchestrator judgment with deterministic, auditable domain-based routing. A fintech auth change should auto-classify as COMPLEX without human intervention.
How It Works
- Input: User task description (string)
- Layer 0: Match keywords from
data/domain-complexity.csv - Layer 1: Analyze task content — classify type and extract mentioned files/modules (load
references/multi-layer-detection.md) - Layer 2: Check project context — files present, directory structure, recent git changes
- Layer 3: Score confidence per domain (HIGH ≥70, MEDIUM 40–69, LOW <40)
- Classify task type — map signals to one of:
bug_fix,feature,refactor,security,devops,docs,review,intake(loadreferences/task-type-classification.md) - Optional: Check
.claude/product-areas.yamlif exists — merge area keywords and paths (seereferences/product-area-config.md) - Output:
{domain, level, workflow, execution_tier, task_type, suggested_skill, confidence, product_area?} - Fallback: No match → return
unknown, defer to manual classification
CSV Schema
| Column | Values | Purpose |
|---|---|---|
| domain | snake_case identifier | Domain name |
| signals | comma-separated keywords | Match against task description |
| level | low, medium, high | Complexity classification |
| workflow | one-shot, standard, enhanced, advanced | Workflow intensity |
| web_searches | comma-separated topics | Suggested research queries |
Routing Logic
| Level | Execution Tier | Gate 1 | Workflow |
|---|---|---|---|
| low | minimal | Bypass eligible (one-shot) | Minimal |
| medium | standard | Required | Standard phases |
| high | high-assurance | Required | Full phases + security |
What ships with it
7 files 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.
- 9d ago First seen · 144 lines · 45 tokens per session scan A 2123f067709e
mk:scale-routing is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 1,553 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
session-deep-dive
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
brainstorm
Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
plugin-dev-workflow
Guide plugin development workflow — editing skills, agents, hooks, or eval framework in this repo. Use when modifying files in plugins/elixir-phoenix/, lab/eval/, or lab/autoresearch/. Ensures changes pass eval, lint, and tests before committing.