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-androidnpx skills add GetStream/agent-skills --skill stream-androidgit clone --depth 1 https://github.com/GetStream/agent-skillsWhat 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 | $0.00128 | $0.03665 |
| Opus 5 | $0.00064 | $0.01833 |
| Sonnet 5 | $0.00026 | $0.00733 |
| Haiku 4.5 | $0.00013 | $0.00366 |
Grade A, and why
stream-android 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 yesterday.
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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stream Android - skill router + execution flow
Rules: Read RULES.md once per session - every non-negotiable rule is stated there, nowhere else.
This file is the single entrypoint: intent classification, local project detection, and module pointers for Stream work in Android apps.
Step 0: Intent classifier (mandatory first - never skip)
Before any tool call, decide the track from the user's input alone - no probes first.
Signals -> track
| Signal in user input | Track |
|---|---|
Explicit product/framework token: Chat Compose, Chat XML, Video Android, Video Compose, Feeds Android, Feeds Compose, etc. |
C - Reference lookup |
| Words "docs" or "documentation" around Stream Android/Compose work | C - Reference lookup |
| "How do I {X} in Compose/XML/Android?", "What does {SDK type/Composable/View/Fragment} do?" | C - Reference lookup |
| "Build me a new Android app", "create a Compose app", "new Android app" + Stream product | A - New app |
| "Add/integrate Stream into this app", "wire Chat/Video/Feeds into my Android project" | B - Existing app |
| "Install Stream packages", "set up Stream in Android Studio", "wire auth/token flow" with no broader feature request | D - Bootstrap / setup |
| Request carries a target appearance - a screenshot, a Figma frame, or "make the chat look like WhatsApp / Telegram / Slack / <app>" | B (or A) + the styling-depth flag below -> design-matching.md |
| "Migrate from Sendbird", "replace the Sendbird Chat SDK with Stream", "we're switching off Sendbird / SendbirdUIKit / uikit-compose" | B + the migration flag below -> sendbird-migration.md |
Bare /stream-android with no args |
List the tracks briefly and wait |
Disambiguation flow
If the request is ambiguous between build/integrate and reference lookup, ask one short question and wait:
Do you want me to wire this into the project, or just map the Android SDK pattern and files?
What ships with it
14 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.
- builder.md 9.6 KB
- credentials.md 7.9 KB
- design-matching.md 45 KB
- references/CHAT-COMPOSE-blueprints.md 30 KB
- references/CHAT-COMPOSE.md 21 KB
- references/CHAT-XML-blueprints.md 28 KB
- references/CHAT-XML.md 16 KB
- references/FEEDS-COMPOSE-blueprints.md 47 KB
- references/FEEDS-COMPOSE.md 26 KB
- references/VIDEO-COMPOSE-blueprints.md 38 KB
- references/VIDEO-COMPOSE.md 23 KB
- RULES.md 11 KB
- sdk.md 4.8 KB
- sendbird-migration.md 31 KB
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.
- yesterday First seen · 198 lines · 128 tokens per session scan A 12b318d98211
stream-android is a skill published in the GitHub repository GetStream/agent-skills (18 stars, last pushed 3d ago), licensed Apache-2.0. It adds 128 tokens to every session and 3,665 once invoked, about $0.0006 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
wukongim-cloud-analysis
Diagnose one exact live WuKongIM cloud Simulation Run or chat-lifecycle Cloud Lease through the repository Analysis MCP. Use when the user or a local Analysis Session asks Codex to inspect a run's cluster state, Prometheus signals, application logs, diagnostics, Controller task audits, profiles, or redacted config…
wukongim-chat-lifecycle
Operate the Codex-owned WuKongIM chat-lifecycle laboratory directly from the local repository. Use when the operator explicitly asks to buy temporary Alibaba Cloud servers and start the repair stability run, deploy a committed candidate to the same Lease, start or monitor the bounded long workload, diagnose a stopped…
wukongim-ops
Diagnose WuKongIM single-node or multi-node clusters through the embedded read-only Operations MCP. Use when investigating cluster health, nodes, physical Slots, exact channel runtime state, Controller tasks, fixed Prometheus signals, raw application logs, diagnostics, redacted config, backups, or bounded pprof…
compare
Multi-model code review. Fan out a bug or task to multiple LLMs, diff their findings, optionally debate, then dispatch subagents to fix in parallel. Use when the user types /compare or asks to compare models on a code issue.
activity-record
Query and orchestrate Arkloop Activity Record local activity data. Covers browser history, search terms, screen time, bluetooth, shell commands, window focus, keyboard, mouse, clipboard, screen content (accessibility tree), microphone audio transcription, and Codex sessions.
geogebra-drawing
GeoGebra 交互式数学可视化 Skill。生成 GGBScript 代码块，支持函数绘图、几何作图、坐标系构建和动态交互。.