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 agentmods add skills/getstream/agent-skills/stream-unrealnpx skills add GetStream/agent-skills --skill stream-unrealgit 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-unreal)<a href="https://agentmods.dev/skills/getstream/agent-skills/stream-unreal"><img src="https://agentmods.dev/badge/skills/getstream/agent-skills/stream-unreal.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 | $0.00175 | $0.03312 |
| Opus 5 | $0.00088 | $0.01656 |
| Sonnet 5 | $0.00035 | $0.00662 |
| Haiku 4.5 | $0.00017 | $0.00331 |
Grade A, and why
stream-unreal 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 6d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stream Unreal - docs orchestrator for Unreal Engine
Chat only. There is no Stream Video or Stream Feeds SDK for Unreal (/video/docs/unreal and the Feeds Unreal index both 404). If the user asks for calling or feeds in Unreal, say so up front and offer the alternatives (a platform SDK on a companion mobile app, or the REST/server API) rather than inventing an API.
The SDK is in beta. IsBetaVersion: true in the .uplugin; the surface can change between releases, and C++ and Blueprint coverage differ per operation. State this whenever the user pins a version or plans an upgrade.
This skill orchestrates: it gates the request against engine support and feature support, routes to the exact docs page, fetches it live, and applies it - while carrying the curated Unreal-specific knowledge the docs do not have (the ApiKey/BeginPlay ordering trap, the UMG widget layer, cooking, and the per-platform config that decides whether a packaged build is usable).
Rules (read once per session): RULES.md - non-negotiable rules + Unreal pitfalls. Read before writing any code.
Step 0: Three gates, before any code
Resolve all three from the user's words plus a read-only probe. Each one can change the answer from "here is the code" to "that is not possible" - so none of them is optional, and none of them belongs in a compile error later.
Gate 1: engine version (picks the release asset, or stops the task)
| Target engine | What to do |
|---|---|
| 5.7 or 5.8 | Supported. Download the matching release asset - see setup.md 2. |
| 4.27 / 5.0 / 5.1 | Only v1.3.0 (Dec 2022) covers these. Say so: the API predates v2.0.0, BlockUser/UnblockUser/GetBlockedUsers do not exist, and none of this skill's v2 guidance is guaranteed to apply. |
| 5.2 through 5.6 | Hard stop - no release supports these. Say it immediately. The options are: upgrade the project to 5.7/5.8, or build the plugin from source against an unsupported engine (unverified, not recommended). Do not download an asset and hope. |
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.
- 6d ago First seen · 159 lines · 175 tokens per session scan A 74339662ef1a
stream-unreal is a skill published in the GitHub repository GetStream/agent-skills (18 stars, last pushed 5d ago), licensed Apache-2.0. It adds 175 tokens to every session and 3,312 once invoked, about $0.0009 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
building-mobile-game
Build mobile games and game-like interactive experiences in React Native and Expo. Use when Codex is creating or refactoring arcade, puzzle, casual, action, physics-based, or animation-heavy gameplay, including Expo game setup with the with-reanimated template, sprite-sheet generation and extraction, frame-based…
minecraft-modpack-server
Host modded Minecraft servers (CurseForge, Modrinth).
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
nano-banana-pro-openrouter
Deterministic OpenRouter image generation adapter for Nano Banana Pro / Gemini image models. Use as skillexec when a meta-skill needs local image files and structured IMAGEREADY records without spawning an LLM agent.
skill-creator-linter
Internal tool (not user-invocable). Called by meta-skill-creator as a DAG step (kind: agent) to lint a candidate meta-skill SKILL.md against G1 (parse + reference check + xmlescape grep + structural lint) and G2 (scheduler dry-run with stub executors). Deterministic, sub-second, no LLM. Returns JSON diagnostics.
paper-abstract-author
Write the abstract after the paper body has been revised, using the final claims and evidence.