What is open-agent-sdk AGENTS.md?

Repository instructions for developing Open Agent SDK, a TypeScript toolkit for building AI agents that use tools and different AI providers. They describe the project layout, required software, commands, and testing-first rules.

Use them when modifying the SDK, running its Bun build and tests, checking types, or adding agent, tool, provider, or permission features.

They give a coding agent the project’s source of truth and working conventions. This reduces the risk of changing the wrong package or skipping required checks.

How OasAIStudio/open-agent-sdk configures Codex and OpenCode

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/AGENTS.md

Clone the repo

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

Made for: Codex, OpenCode.

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/agents-md/github.svg)](https://agentmods.dev/instructions/oasaistudio/open-agent-sdk/agents-md)

Your own site

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

Per session 551 This file is loaded in full into every session.

When invoked 551 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	$0.00551	$0.00551
Opus 5.5	$0.00220	$0.00220
Sonnet 5.5	$0.00110	$0.00110
Haiku 4.5	$0.00055	$0.00055

Measured 2mo ago against content hash cc635ab546fe, 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 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 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.

AGENTS.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Open Agent SDK - Codex Agent Guide

This file defines how Codex should work in this repository.

Goal

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

Source Of Truth

Product requirements: REQUIREMENTS.md
Architecture decisions: docs/adr/
Gap analysis: docs/gap-analysis.md
Git workflow: docs/workflows/git-workflow.md
Testing guide: docs/workflows/testing-guide.md

Repository Layout

Root workspace: Bun workspaces monorepo
Core package: packages/core/
Source code: packages/core/src/
Tests: packages/core/tests/ (mirror src/ structure)

Runtime And Language

Runtime: Bun >= 1.0.0
Language: TypeScript 5.x, strict mode

Commands

Install deps: bun install
Build: bun run build
Test: bun test
Coverage: bun test --coverage
Type check: bun run typecheck

For integration tests with real LLM APIs:

env $(cat .env | xargs) bun test

Engineering Rules

TDD Policy

Use tests-first for:

Core agent logic (ReAct loop, tool execution, subagent spawning)
Tool implementations
Provider integrations
Permission system

Tests-after is acceptable for:

Docs changes
Config updates
Simple utilities
Obvious low-risk fixes

Quality Bar

Keep public APIs fully typed
Preserve backward compatibility unless explicitly requested
Add or update tests for behavior changes
Keep changes minimal and focused (one logical change per PR)

Git And PR

Use Conventional Commits: type(scope): description
PR title/description/comments in English
Never push new changes to a branch whose PR is already merged
If branch is merged, create a new branch from latest main

Codex-Specific Operating Rules

Prefer rg for search (rg --files for file listing)
Read before edit; avoid broad refactors unless required
Do not run destructive git commands unless explicitly requested
Do not revert unrelated local changes
Validate with targeted tests first, then broader tests if needed
Summarize exact files changed and verification commands run

Read the full file on GitHub · 85 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 · 85 lines · 551 tokens per session scan A cc635ab546fe

Subscribe to this mod's changes

open-agent-sdk AGENTS.md is an instructions file published in the GitHub repository OasAIStudio/open-agent-sdk (46 stars, last pushed 7mo ago), licensed MIT. It adds 551 tokens to every session, about $0.0022 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 AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
open-agent-sdk AGENTS.mdOasAIStudio/open-agent-sdk	Instructions file	46	7mo ago	MIT	A	551	Codex, OpenCode
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 Codex