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 GetStream/agent-skills --skill stream-unitygit clone --depth 1 https://github.com/GetStream/agent-skillsWrote 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/getstream/agent-skills/stream-unity)<a href="https://agentmods.dev/skills/getstream/agent-skills/stream-unity"><img src="https://agentmods.dev/badge/skills/getstream/agent-skills/stream-unity/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/getstream/agent-skills/stream-unity"><img src="https://agentmods.dev/badge/skills/getstream/agent-skills/stream-unity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00211 | $0.04867 |
| Opus 5.5 | $0.00084 | $0.01947 |
| Sonnet 5.5 | $0.00042 | $0.00973 |
| Haiku 4.5 | $0.00021 | $0.00487 |
Grade A, and why
stream-unity scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Bash(curl -sL *), How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stream Unity - docs orchestrator for Unity Engine
Chat and Video. There is no Stream Feeds SDK for Unity (/activity-feeds/docs/unity and https://getstream.io/cli/docs/activity-feeds-unity.md both 404). If the user asks for activity feeds in Unity, say so up front and offer the alternatives (the REST/server API driven from your backend, or a platform SDK on a companion app) rather than inventing an API.
These are two separate SDKs, and almost nothing is shared. Different repos, different install mechanisms, different maturity, different supported platforms, different docs quality. There is no combined client, no shared AuthCredentials type (StreamChat.Libs.Auth.AuthCredentials and StreamVideo.Libs.Auth.AuthCredentials are distinct types in distinct assemblies), and connecting a user to one does not connect them to the other. Treat "add chat to my Unity call app" as two integrations that happen to share an API key.
| Chat | Video | |
|---|---|---|
| Repo | GetStream/stream-chat-unity (default branch develop) |
GetStream/stream-video-unity (default branch main) |
| Latest | v5.7.0 (stable, 5.x line) | 0.11.0 (pre-1.0 - the surface still moves) |
| Install | .unitypackage from GitHub Releases, imported into Assets/ |
UPM package from a git URL |
| Entry point | StreamChatClient.CreateDefaultClient() -> IStreamChatClient |
StreamVideoClient.CreateDefaultClient() -> IStreamVideoClient |
| Namespace | StreamChat.Core |
StreamVideo.Core |
| Platforms | Everything Unity targets, WebGL included | Android (ARM64), iOS, Windows x64, macOS, Linux. No WebGL, no UWP |
| Pre-built UI | None - a sample project, not components | None - a sample project, not components |
| Docs coverage | Good: nearly every page carries real Unity C# | Thin: 22 pages; several shipped capabilities have no page at all |
Neither SDK ships reusable UI. Both ship a sample project you import and read, not a component library you drop in. Every chat bubble, channel row, participant tile, and call button in the user's game is code you write. Say this before promising a screen, and run ui.md when building one.
This skill orchestrates: it gates the request against product, platform, and feature support, routes to the exact docs page, fetches it live, and applies it - while carrying the Unity-specific knowledge the docs do not have (the client's hidden DontDestroyOnLoad runner, the track-binding requirement, IL2CPP stripping, and the player settings that decide whether a build works on device at all).
Rules (read once per session): RULES.md - non-negotiable rules + Unity pitfalls. Read before writing any code.
What ships with it
5 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.
- 1mo ago First seen · 220 lines · 211 tokens per session scan A 47f45aedbe76
stream-unity is a skill published in the GitHub repository GetStream/agent-skills (20 stars, last pushed 2d ago), licensed Apache-2.0. It adds 211 tokens to every session and 4,867 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
unity-csharp
A set of practical guidelines for writing Unity game scripts in C#. Unity is a game engine, and these rules cover its update loop, object lifetime, memory cleanup, coroutines, and editable data.
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…
agentscope-java
Expert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or…
script-execute
Compiles and executes C# code dynamically using Roslyn. Supports a full-code mode (default) and a body-only mode — see the skill body for the difference and for how to pass Unity object references as parameters.
stack-trace-go-probe
Internal helper for meta-stack-trace-investigator. Use when a Go panic or stack trace needs Go-specific nil/error checks, go test reproducer guidance, and patch targets.
stack-trace-python-probe
Internal helper for meta-stack-trace-investigator. Use when a Python traceback needs Python-specific root-cause checks, pytest reproducer guidance, and defensive patch targets.