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/deuz-ai/deuz-sdk/agents-mdgit clone --depth 1 https://github.com/Deuz-AI/Deuz-SDKWrote 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/instructions/deuz-ai/deuz-sdk/agents-md)<a href="https://agentmods.dev/instructions/deuz-ai/deuz-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/deuz-ai/deuz-sdk/agents-md.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 | $0.00444 | $0.00444 |
| Opus 5 | $0.00222 | $0.00222 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
Deuz-SDK 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 5d 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.
What it actually says
Learned User Preferences
- Prefer Turkish for chat replies when the user writes in Turkish; do not answer in Russian unless they ask for it.
- Challenge odd semver / release-doc names (e.g.
1.9.9) and steer to the real minor (1.9.0) before writing root design docs. - Keep README and public messaging realistic: position the SDK as a practical tool on the path toward ASI, not hype.
- Product bar for major work: Manus-style full autonomy, and compete with Mastra / Vercel AI SDK (aim near #2 among SDKs).
- Prefer Cursor AskQuestion-style turn endings over QingTian /
check_messagesMCP loops when those channels are disallowed. - After a task is fully done, ask in Turkish whether to close the chat or if they want to add anything (unless they say to answer without closing).
- Treat dedicated AWS Bedrock and Azure OpenAI / Azure AI factories as wanted gaps to add and document clearly.
Learned Workspace Facts
- npm-workspaces monorepo publishing
@deuz-sdk/core(edge-safe AI SDK) and@deuz-sdk/react(thin React adapter). - Code-verified release design specs live at the repo root as
X.Y.Z.md(e.g.1.9.0.md); planning notes are often Turkish while public README/docs stay English. - 1.8.0 “Otonom Ajan Runtime” centers on workspace, compute/CodeAct, planner→executor→verifier autonomy, browser, background runtime, plus published
./providersand./testingsubpaths. - OpenAI-compatible routers (Mistral, DeepSeek, Qwen, Moonshot/Kimi, Groq, etc.) ship under
@deuz-sdk/core/providers, not as first-class dedicated factories like./anthropic/./openai. - Dedicated factory gaps called out in recent work: AWS Bedrock and Azure OpenAI / Azure AI.
- Core stays Web-API / edge-safe by default; Node-only code belongs under
src/node/**or other exempt Node subpaths.
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.
- 5d ago First seen · 19 lines · 444 tokens per session scan A 0b663d8db395
Deuz-SDK AGENTS.md is an instructions file published in the GitHub repository Deuz-AI/Deuz-SDK (1,291 stars, last pushed 22d ago), licensed MIT. It adds 444 tokens to every session, about $0.0022 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
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
openai-agents-python AGENTS.md
AGENTS.md instructions for openai/openai-agents-python, covering contributor guide, policies & mandatory rules, mandatory skill usage, work status reporting and git worktree and branch safety.
LangBot AGENTS.md
AGENTS.md instructions for langbot-app/LangBot, covering agents.md, quick facts, essential commands, where to look and cross-repo sdk work.
open-multi-agent AGENTS.md
AGENTS.md instructions for open-multi-agent/open-multi-agent, covering agents.md, repository map, commands, working rules and validation by change type.
UltraRAG AGENTS.md
AGENTS.md instructions for OpenBMB/UltraRAG, covering agents.md, 1) project identity, 2) repository map (what matters most), 3) mental model of the system and 4) two-phase execution lifecycle.
gptme AGENTS.md
AGENTS.md instructions for gptme/gptme, covering agent instructions for gptme, git workflow, code style, testing and project structure.