What is open-agent-sdk CLAUDE.md?

A repository instruction file for a TypeScript software development kit used to build AI agents with tools, step-by-step reasoning loops, and different language-model providers. It documents the project layout, requirements, architecture decisions, testing, and workflow.

It is for guiding work on agent tools, model-provider adapters, sessions, permissions, skills, hooks, and tests in the SDK.

It gives the agent the context needed to navigate the SDK and follow its existing design and testing rules instead of guessing how new code should fit.

How OasAIStudio/open-agent-sdk configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to OasAIStudio/open-agent-sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/OasAIStudio/open-agent-sdk/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/OasAIStudio/open-agent-sdk

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/oasaistudio/open-agent-sdk/claude-md/github.svg)](https://agentmods.dev/instructions/oasaistudio/open-agent-sdk/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/oasaistudio/open-agent-sdk/claude-md"><img src="https://agentmods.dev/badge/instructions/oasaistudio/open-agent-sdk/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/oasaistudio/open-agent-sdk/claude-md"><img src="https://agentmods.dev/badge/instructions/oasaistudio/open-agent-sdk/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 821 This file is loaded in full into every session.

When invoked 821 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00821	$0.00821
Opus 5.5	$0.00328	$0.00328
Sonnet 5.5	$0.00164	$0.00164
Haiku 4.5	$0.00082	$0.00082

Measured 2mo ago against content hash 196a0ad45f75, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

open-agent-sdk CLAUDE.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 2mo 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.

CLAUDE.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Open Agent SDK - Claude Code Context

TypeScript SDK for building AI agents with tool use, ReAct loop, and multi-provider support.

Document	Purpose
Requirements	Feature requirements
Gap Analysis	vs Claude Agent SDK
ADRs	Architecture decisions
Git Workflow	Worktree & PR rules
Testing Guide	TDD & env setup

Project Structure

open-agent-sdk/
├── CLAUDE.md              # This file: Claude Code context
├── package.json           # Bun workspaces configuration
├── REQUIREMENTS.md        # Product requirements
└── packages/
    └── core/              # Core SDK package
        ├── src/
        │   ├── index.ts      # Public API exports
        │   ├── types/        # Message, tool, provider types
        │   ├── tools/        # Tool implementations
        │   ├── providers/    # LLM provider adapters
        │   ├── agent/        # ReAct loop, subagent system
        │   ├── session/      # Session management
        │   ├── permissions/  # Permission system
        │   ├── skills/       # Skill loading system
        │   └── hooks/        # Hooks framework
        └── tests/            # Test files (mirror src/ structure)

Tech Stack

TypeScript 5.x (strict), Bun runtime
Testing: Bun test framework
Dependencies: ai (Vercel AI SDK), @ai-sdk/google, zod

Decision Rules

TDD

Use TDD for: Core agent logic, tools, providers, permissions
Tests after OK for: Utils, docs, config, obvious fixes

Worktrees

Recommended for: Features, refactoring, experiments
Optional for: Typo fixes, single-line fixes, hotfixes
See Git Workflow

Commits

Format: type(scope): description (Conventional Commits)
Frequency: After each logical unit
Language: English only
Incremental: Break features into multiple commits

Read the full file on GitHub · 97 lines

Changes

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.

2mo ago First seen · 97 lines · 821 tokens per session scan A 196a0ad45f75

Subscribe to this mod's changes

open-agent-sdk CLAUDE.md is an instructions file published in the GitHub repository OasAIStudio/open-agent-sdk (46 stars, last pushed 7mo ago), licensed MIT. It adds 821 tokens to every session, about $0.0033 per session on Opus 5.5. 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.

Building agents LLM agent ai ai-agent ai-sdk build-in-public

open-agent-sdk CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
open-agent-sdk CLAUDE.mdOasAIStudio/open-agent-sdk	Instructions file	46	7mo ago	MIT	A	821	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

open-agent-sdk: Instructions file for Claude Code