codex-agent-sdk-go: Instructions file for Claude Code

CLAUDE.md

codex-agent-sdk-go CLAUDE.md is an instructions file for Claude Code from hishamkaram/codex-agent-sdk-go. It costs 1,528 tokens per session, scanned A, original, MIT.

A Go software library for controlling the OpenAI Codex command-line agent through a typed programming interface. It starts the Codex app server and exchanges structured messages for threads, turns, events, approvals, and tool settings.

In plain words
What is it for?
Building, testing, checking, and integrating Go applications with Codex threads, streamed events, approvals, and MCP configuration.
Why use it?
It lets Go programs use Codex agent conversations and streaming results without implementing the communication protocol themselves.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code; mentions Codex.

This is hishamkaram/codex-agent-sdk-go's own configuration. It tells Claude Code how to work on codex-agent-sdk-go itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything codex-agent-sdk-go configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/hesham/.claude/plans/jaunty-crafting-flamingo.md.

Reuse

Borrowing it

Nothing to install: this file belongs to hishamkaram/codex-agent-sdk-go. 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/hishamkaram/codex-agent-sdk-go/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/hishamkaram/codex-agent-sdk-go

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.

agentmods badge for codex-agent-sdk-go CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hishamkaram/codex-agent-sdk-go/claude-md.svg)](https://agentmods.dev/instructions/hishamkaram/codex-agent-sdk-go/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/hishamkaram/codex-agent-sdk-go/claude-md"><img src="https://agentmods.dev/badge/instructions/hishamkaram/codex-agent-sdk-go/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,528 This file is loaded in full into every session.
When invoked 1,528 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01528 $0.01528
Opus 5 $0.00764 $0.00764
Sonnet 5 $0.00306 $0.00306
Haiku 4.5 $0.00153 $0.00153

Measured 7d ago against content hash dd3c25ff40d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

codex-agent-sdk-go 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 7d 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 · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Agent SDK for Go

What This Is

Go SDK for the OpenAI Codex CLI app-server transport — spawns codex app-server as a subprocess, speaks JSON-RPC 2.0 over stdio (line-framed, jsonrpc field omitted), and exposes a typed Go API for threads, turns, streaming events, approvals, and MCP configuration.

Module: github.com/hishamkaram/codex-agent-sdk-go | Go: 1.25.8+ | License: MIT

Sibling SDK: claude-agent-sdk-go wraps the Claude Code CLI the same way.

Build & Test

go build ./...                            # Build all packages
go test -race -count=1 -p 4 -short ./... # Unit tests (fast, no CLI needed)
make test-integration                     # Integration tests (require real codex CLI + OPENAI_API_KEY)
go vet ./...                              # Static analysis
golangci-lint run ./...                   # Linter
govulncheck ./...                         # Vulnerability scan

Architecture

Package Path Purpose
root ./ Public API: Codex client, Query(), NewClient(), thread operations
types types/ Public types: events, items, options, approvals, errors
transport internal/transport/ Subprocess spawn, CLI discovery, line-framed stream I/O
jsonrpc internal/jsonrpc/ JSON-RPC 2.0 framing + request/notification/server-request demux
events internal/events/ Notification payload → typed event translation
log internal/log/ zap wrapper (constructor-injected)

Critical Rules

Transport: JSON-RPC 2.0 line-framed, LF terminator, omit "jsonrpc":"2.0" on the wire (server tolerates absence; matches upstream Python SDK). Read-side buffer minimum 2 MiB — user input cap is 1 MiB and envelope overhead pushes some notifications past that.

Stdin serialization: a single sync.Mutex MUST serialize every stdin write across all frame types (user turn/start, approval responses, config writes). Frames may NOT interleave on the wire.

Read the full file on GitHub · 106 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.

  1. 7d ago First seen · 106 lines · 1,528 tokens per session scan A dd3c25ff40d8

Subscribe to this mod's changes

codex-agent-sdk-go CLAUDE.md is an instructions file published in the GitHub repository hishamkaram/codex-agent-sdk-go (5 stars, last pushed yesterday), licensed MIT. It adds 1,528 tokens to every session, about $0.0076 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 2026-08-31.

Related

Other instructions, from other repositories

awesome-ai-rules copilot-instructions.md

Instructions for Lay4U/awesome-ai-rules, covering github copilot instructions: go, inline completion priorities, go api conventions, interfaces and error patterns.

Lay4U/awesome-ai-rules · 396 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens