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 XeldarAlz/everything-claude-unity --skill model-routinggit clone --depth 1 https://github.com/XeldarAlz/everything-claude-unityWrote 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/xeldaralz/everything-claude-unity/model-routing)<a href="https://agentmods.dev/skills/xeldaralz/everything-claude-unity/model-routing"><img src="https://agentmods.dev/badge/skills/xeldaralz/everything-claude-unity/model-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 | $0.00037 | $0.00880 |
| Opus 5 | $0.00018 | $0.00440 |
| Sonnet 5 | $0.00007 | $0.00176 |
| Haiku 4.5 | $0.00004 | $0.00088 |
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 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Routing Heuristics
When delegating work to agents, use these signals to select the right model tier. These are heuristics, not hard rules — the user can always override with --quick or --thorough.
Complexity Signals
| Signal | Simple (haiku/sonnet) | Moderate (sonnet) | Complex (opus) |
|---|---|---|---|
| File count | 1-2 files | 3-8 files | 9+ files |
| Scope | Single class/method | Single system | Multiple systems |
| Keywords | "add field", "rename", "fix typo", "remove" | "implement", "refactor", "test" | "architect", "migrate", "optimize", "redesign" |
| Risk level | No serialization, no networking | Serialization involved | Networking, threading, platform-specific |
| Patterns | Obvious fix, boilerplate | Requires design choices | Requires trade-off reasoning |
Routing Decision Matrix
Haiku Tier — Fast, Cheap, Read-Only
Agents: unity-scout, unity-linter
Use when:
- Quick codebase exploration before a larger task
- Fast validation pass (lint-style check)
- Finding files, symbols, or patterns
- Pre-flight checks before delegating to a heavier agent
Never use for: Writing code, modifying files, complex reasoning
Sonnet Tier — Balanced Speed/Quality
Agents: unity-coder-lite, unity-fixer-lite, unity-reviewer, unity-test-runner, unity-build-runner, unity-migrator, unity-security-reviewer, unity-git-master
Use when:
- Single-file changes with clear requirements
- Code review against a known checklist
- Writing tests for existing code
- Build configuration
- Bug fixes where the cause is known or obvious
- Structured tasks with documented procedures (migrations, LFS setup)
Opus Tier — Deep Reasoning
Agents: unity-coder, unity-fixer, unity-verifier, unity-optimizer, unity-prototyper, unity-shader-dev, unity-scene-builder, unity-ui-builder, unity-network-dev, unity-critic
Use when:
- Multi-system feature implementation
- Bug investigation requiring deep analysis
- Performance optimization (trade-off reasoning)
- Architecture decisions
- Shader math and visual programming
- Spatial reasoning (scene building)
- Challenging plans (critic role)
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 · 81 lines · 37 tokens per session scan A c61790b1f83e
model-routing is a skill published in the GitHub repository XeldarAlz/everything-claude-unity (22 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 880 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 2026-08-30.
Other skills, from other repositories
Read, create and manipulate PDF files — extract text and tables, merge, split, rotate, reorder and delete pages, read and fill AcroForm fields, add or strip metadata, encrypt and decrypt, and generate new PDFs from HTML or from scratch. Also covers rasterising pages to images so a PDF can actually be looked at, and…
xlsx
Create, read and edit Microsoft Excel .xlsx spreadsheets — data tables, formulas, multiple sheets, number formats, conditional formatting, charts, frozen panes and named ranges. Also covers reading an existing workbook to extract values or formulas, recalculating formulas so cached values are correct, converting to…
rove
Use when controlling Rove tasks, parallel coding attempts, hosted agent sessions, task lifecycle, or the daemon-owned issue tracker from a shell. Also the ONLY channel for messaging another agent session on this machine — rove api send, never a peer/MCP side channel.
django-admin-customization
Customize Django admin: ModelAdmin, inline models, custom actions, listdisplay, listfilter, search, admin site customization, and custom views. Use when the user configures Django admin, asks about admin customization, registers models, or needs admin-side data management features. Trigger when you see bare…
context-management
Strategies for managing AI agent context windows including optimization, summarization, retrieval-augmented generation, progressive disclosure, and pruning. Use when the user is hitting context limits, building long-running agents, implementing RAG, optimizing token usage, or designing systems that need to manage…
deploy-strategies
Guide for deployment strategies including blue-green, canary, rolling updates, feature flags, and rollback procedures. Use when the user asks about deployment patterns, zero-downtime deployments, release strategies, or rollback plans. Trigger whenever deployment, release management, or production rollout is discussed.