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 dyCuong03/unity-agent-team --skill routinggit clone --depth 1 https://github.com/dyCuong03/unity-agent-teamWrote 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/dycuong03/unity-agent-team/routing)<a href="https://agentmods.dev/skills/dycuong03/unity-agent-team/routing"><img src="https://agentmods.dev/badge/skills/dycuong03/unity-agent-team/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/dycuong03/unity-agent-team/routing"><img src="https://agentmods.dev/badge/skills/dycuong03/unity-agent-team/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 | $0.00041 | $0.02966 |
| Opus 5.5 | $0.00016 | $0.01186 |
| Sonnet 5.5 | $0.00008 | $0.00593 |
| Haiku 4.5 | $0.00004 | $0.00297 |
Grade A, and why
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 11d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity Skill Router
Status
Unity-Skills routing layer vendored at .claude/skills/unity-skills/
(upstream Besty0728/Unity-Skills v1.9.2 — see
.claude/skills/unity-skills/VERSION). 69 module SKILL.md files are
available locally; the orchestrator can resolve every @.claude/skills/ unity-skills/skills/<module>/SKILL.md reference without a missing-file
fallback. The Unity Editor package (com.besty.unity-skills) must still
be installed into the consuming Unity project for REST calls to
http://localhost:8090 to succeed.
Purpose
Select the minimum set of Unity-Skills modules to load for a given task. Prevent prompt bloat. Maximize relevance. Preserve DOTS-first policy.
Domain Gating (MANDATORY — applies before keyword routing)
The classifier from .claude/docs/rules/dual-stack-domain-system.md runs first.
Its output decides which side of the catalog the router is even allowed to
draw from:
| Triage domain | Layer 1 (DOTS) | Layer 2 (Unity Foundation) | Layer 3 (unity-skills modules) |
|---|---|---|---|
| DOTS (Domain 1) | Heavy — always | Light — always | Skip by default. Load only if a unity-skills module is explicitly required by a hybrid touchpoint (e.g. Baker authoring, presentation bridge). MonoBehaviour-first modules are forbidden in this domain. |
| Unity (Domain 2) | Light — advisory only | Heavy — always | Primary source. Use the keyword table below. Max 2 domain + 2 advisory. |
| Hybrid (Domain 3) | Heavy — DOTS owns runtime truth | Heavy — Unity owns presentation | Both sides loaded. Pick one DOTS-side concern and one Unity-side concern; verification-contract.md requires the bridge contract be documented in workspace/design.md. |
| Ambiguous | Layer 1 + 2 only | Layer 1 + 2 only | None — escalate to architect per escalation-rules-domain.md. |
Hard scoping rules:
- DOTS domain → never load
ui,animator,navmesh,dotween,event,gameobject,component(all MonoBehaviour-first; seeunity-skills-conflicts.md). The ecs-penalty modifier inskill-confidence-routing.mdalready drops these below threshold; the router must respect that and not bypass it. - Unity domain → never load burst, scheduling, native-container, ECS job pattern advisory unless DOTS APIs are detected in touched code.
- Hybrid domain → BOTH allowed, but the bridge direction is one-way
(DOTS writes state, Unity reads). Verify this in
ownership-boundaries.md. - Loaded module budget (any domain): max 2 domain + 2 advisory per agent
per task. The confidence threshold ≥ 0.70 from
skill-confidence-routing.mdstill applies.
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.
- 11d ago First seen · 227 lines · 41 tokens per session scan A 999d228255b0
routing is a skill published in the GitHub repository dyCuong03/unity-agent-team (7 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 2,966 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
playtest-report
Structured playtest report template, or turn existing playtest notes into structured feedback.
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
motion
Reconstruct a skeleton from calibrated mesh projections and sequential VLM joint annotations, then fit joints and skin weights. Generate motion from joint-position trajectories, rhythm and contact constraints through IK; refine bone orientation against the action, then export, retarget and validate on the target mesh.