goai: Instructions file for Codex

AGENTS.md

goai AGENTS.md is an instructions file for Codex, OpenCode from zendev-sh/goai. It costs 1,262 tokens per session, scanned A, original, MIT.

Contributor instructions for the GoAI codebase, including its commands, layout, architecture, rules, and guidance for adding providers. A provider is the service that supplies an AI model.

In plain words
What is it for?
Use them when working on GoAI, running its checks, understanding where code belongs, handling errors and retries, or adding an AI provider.
Why use it?
They give contributors a shared reference for building, testing, linting, and changing the project without overlooking its conventions.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is zendev-sh/goai's own configuration. It tells Codex and OpenCode how to work on goai 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 goai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zendev-sh/goai. 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/zendev-sh/goai/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/zendev-sh/goai

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.

agentmods badge for goai AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zendev-sh/goai/agents-md/github.svg)](https://agentmods.dev/instructions/zendev-sh/goai/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zendev-sh/goai/agents-md"><img src="https://agentmods.dev/badge/instructions/zendev-sh/goai/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.

agentmods 80×15 button for goai AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zendev-sh/goai/agents-md"><img src="https://agentmods.dev/badge/instructions/zendev-sh/goai/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,262 This file is loaded in full into every session.
When invoked 1,262 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 $0.01262 $0.01262
Opus 5.5 $0.00505 $0.00505
Sonnet 5.5 $0.00252 $0.00252
Haiku 4.5 $0.00126 $0.00126

Measured 6d ago against content hash 7de80d11b57a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

goai 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 6d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - GoAI

Instructions for AI contributors working on the GoAI codebase.

Commands

go build ./...          # Build
go test ./...           # Test all packages
go test -cover ./...    # Test with coverage
golangci-lint run       # Lint
go test ./provider/openai/  # Test single package

Architecture

GoAI is a Go SDK for AI applications - one API across 25+ LLM providers. Inspired by Vercel AI SDK, adapted to Go idioms.

goai/
├── generate.go             # GenerateText, StreamText
├── object.go               # GenerateObject[T], StreamObject[T]
├── embed.go                # Embed, EmbedMany
├── image.go                # GenerateImage
├── video.go                # GenerateVideo
├── realtime.go             # OpenRealtimeSession (experimental realtime voice sessions)
├── options.go              # WithPrompt, WithTools, etc.
├── schema.go               # SchemaFrom[T] - JSON Schema from Go structs
├── errors.go               # APIError, ContextOverflowError
├── retry.go                # Exponential backoff (errors.As, not type assertion)
├── caching.go              # Prompt cache control (copies msgs, no mutation)
├── types.go                # Tool struct
├── messages.go             # Message builders
├── hooks.go                # Telemetry hooks
├── partial_json.go         # Partial JSON parser for streaming
├── provider/
│   ├── provider.go         # LanguageModel, EmbeddingModel, ImageModel, VideoModel, RealtimeModel interfaces
│   ├── realtime.go         # Realtime audio formats, params, events, capabilities
│   ├── types.go            # Message, Part, Usage, StreamChunk
│   ├── token.go            # TokenSource, CachedTokenSource (lock-free fetch)
│   ├── openai/             # OpenAI (Chat Completions + Responses API)
│   ├── anthropic/          # Anthropic (Messages API)
│   ├── google/             # Google Gemini (REST + Live realtime)
│   ├── bedrock/            # AWS Bedrock (Converse API + SigV4 + EventStream, RWMutex for fallback; InvokeModel API for embeddings)
│   ├── vertex/             # Vertex AI
│   ├── azure/              # Azure OpenAI
│   ├── cohere/             # Cohere (Chat v2 + Embed)
│   ├── minimax/            # MiniMax (Anthropic-compat, delegates to anthropic/)
│   ├── compat/             # Generic OpenAI-compatible
│   └── <22 more>/          # Mostly OpenAI-compat (some via compat/ or anthropic/ wrappers)
│ # tools.go files: 5 files with provider-defined tools: anthropic/ (14 tools), openai/ (4 tools), google/ (5 tools), xai/ (2 tools), groq/ (1 tool)
├── internal/
│   ├── openaicompat/       # Shared codec for 22 provider implementation files
│   ├── gemini/             # Schema sanitization (Vertex, Google)
│   ├── sse/                # SSE parser
│   ├── httpc/              # HTTP helpers + ParseDataURL
│   └── realtimews/         # Provider-neutral WebSocket transport for realtime adapters
├── mcp/                    # MCP (Model Context Protocol) client
├── observability/
│   ├── langfuse/           # Langfuse observability integration (separate go.mod)
│   └── otel/               # OpenTelemetry tracing and metrics (separate go.mod)
├── examples/               # 33 runnable examples (including 8 MCP examples)
└── bench/                  # Performance benchmarks (GoAI vs Vercel AI SDK)

Read the full file on GitHub · 90 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. 6d ago Changed 7de80d11b57a
  2. 9d ago Changed c27452d25e55
  3. 18d ago Changed · +3 lines · +80 tokens per session b2b1781c786c
  4. 28d ago Changed 947827066ca9
  5. 1mo ago Changed · +12 tokens per session 6a278e202a77
  6. 2mo ago Changed a04dfaa9fbf6
  7. 2mo ago First seen · 87 lines · 1,170 tokens per session scan A 1adc9df404f2

Subscribe to this mod's changes

goai AGENTS.md is an instructions file published in the GitHub repository zendev-sh/goai (234 stars, last pushed 6d ago), licensed MIT. It adds 1,262 tokens to every session, about $0.0050 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.

Related

goai AGENTS.md compared with instructions from other repositories

goai AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
goai AGENTS.mdzendev-sh/goaiInstructions file2346d agoMITA1,262Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode