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 instructions/getstream/agent-skills/agents-mdgit 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 | $0.01069 | $0.01069 |
| Opus 5 | $0.00535 | $0.00535 |
| Sonnet 5 | $0.00214 | $0.00214 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
agent-skills AGENTS.md 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 2d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Codex entrypoint for the Stream skill pack
The pack has a generic router (which includes the CLI), core specialists, and platform peers declared in skills/stream/peers.yaml.
Router (start here): skills/stream/SKILL.md - classifies intent, dispatches to a sub-skill, and runs getstream CLI commands.
Rules (read once per session): skills/stream/RULES.md - core web, CLI, docs, and peer-pack routing rules. Platform sub-skills can add their own RULES.md.
Sub-skills
| Sub-skill | Use for |
|---|---|
skills/stream-docs/SKILL.md |
Search live SDK documentation from getstream.io (no CLI required) |
skills/stream-react/SKILL.md |
Default for web React/Next.js. Scaffold, enhance, audit, or migrate a React/Next.js app with Chat/Video/Feeds/Moderation |
skills/stream-builder/SKILL.md |
Framework-agnostic builder - only when named explicitly; web React/Next.js defaults to stream-react |
skills/stream-swift/SKILL.md |
Build or integrate Stream Chat/Video/Feeds in Swift/SwiftUI/UIKit/iOS apps |
skills/stream-flutter/SKILL.md |
Build or integrate Stream Chat in Flutter apps (stream_chat_flutter and stream_chat_flutter_core) |
skills/stream-unity/SKILL.md |
Build or integrate Stream Chat and Stream Video in Unity Engine projects (C#). Chat + Video - no Feeds SDK for Unity |
skills/stream-unreal/SKILL.md |
Build or integrate Stream Chat in Unreal Engine 5.7/5.8 projects (C++ and Blueprint). Chat only - no Video or Feeds SDK for Unreal |
skills/stream-feeds-migration/SKILL.md |
Generate the v2 -> v3 Activity Feeds sync mapping by sampling the v2 app's live activities and reactions. No CLI and no project required - it emits a config object |
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.
- 2d ago First seen · 44 lines · 1,069 tokens per session scan A 6875d3e001bd
agent-skills AGENTS.md is an instructions file published in the GitHub repository GetStream/agent-skills (18 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,069 tokens to every session, about $0.0053 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 instructions, from other repositories
ii-agent AGENTS.md
Instructions for Intelligent-Internet/ii-agent, covering ii-agent contributor guide, quick start, repository map, mandatory rules and architecture.
cyrus copilot-instructions.md
Copilot instructions for cyrusagents/cyrus: Note, there is a need to maintain the use of '--print' when running the claude exec commands because that is what makes it non-interactive.
framework AGENTS.md
Instructions for ai-driven-dev/framework, covering agents.md, behavior, communication, action and memory management.
agnix bad-frontmatter.instructions.md
Instructions for agent-sh/agnix, a project described as: The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP. Plugin for all major IDEs included, with autofixes.
polysona CLAUDE.md
Instructions for LilMGenius/polysona, covering polysona, philosophy (agent-enforced), behavioral rules (no exceptions), context loading protocol and data conventions.
skills CLAUDE.md
Instructions for capawesome-team/skills, covering claude.md, project overview, repository structure, skill.md format and writing agent-optimized skills.