What is coze-sdk-gen AGENTS.md?

A set of repository instructions for coding agents working on a software development kit generator.

Use it to guide SDK generation from an OpenAPI description and compare the result with Python and Go reference repositories while requiring linting, tests, builds, and other checks.

It defines the required inputs, workflow limits, implementation rules, and checks so generated code can be reviewed and reproduced.

How coze-dev/coze-sdk-gen configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to coze-dev/coze-sdk-gen. 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/coze-dev/coze-sdk-gen/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/coze-dev/coze-sdk-gen

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/coze-dev/coze-sdk-gen/agents-md/github.svg)](https://agentmods.dev/instructions/coze-dev/coze-sdk-gen/agents-md)

Your own site

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

Per session 2,931 This file is loaded in full into every session.

When invoked 2,931 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	$0.02931	$0.02931
Opus 5.5	$0.01172	$0.01172
Sonnet 5.5	$0.00586	$0.00586
Haiku 4.5	$0.00293	$0.00293

Measured 1mo ago against content hash 1067f729a25e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

coze-sdk-gen 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 1mo 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 · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Background

This document defines execution rules for coze-sdk-gen, targeting automated coding agents (for example Codex/Claude), with the goal of a reproducible and auditable implementation process.

Style Reference (AGENTS.md / CLAUDE.md)

This file follows common AGENTS.md / CLAUDE.md best practices:

Define objective, inputs, outputs, and acceptance criteria first.
Explicitly define allowed vs. disallowed behavior (especially no direct copy from baseline SDKs).
Constrain workflow before implementation details.
Require verifiable checks for every change (lint / test / build, and diffgo for Go baseline alignment).
Priority order: this file > temporary verbal preference > default behavior.

Inputs and Baseline Repositories

Swagger input: coze-openapi.yaml
Python baseline repository: https://github.com/coze-dev/coze-py
- Local baseline mirror directory: choose a local path for coze-py (for example <baseline-root>/coze-py)
Go baseline repository: https://github.com/coze-dev/coze-go
- Local baseline mirror directory: choose a local path for coze-go (for example <baseline-root>/coze-go)

Repository Bootstrap

If baseline repositories are missing locally, they must be cloned before generation/alignment:

mkdir -p <baseline-root>
test -d <baseline-root>/coze-py || git clone https://github.com/coze-dev/coze-py <baseline-root>/coze-py
test -d <baseline-root>/coze-go || git clone https://github.com/coze-dev/coze-go <baseline-root>/coze-go

Core Implementation Principles

1) Swagger-First (Default)

Non-special files (by default, all files) must be produced via Swagger parsing + generation logic.
Direct copying/overwriting from local baseline mirrors (coze-py / coze-go) is forbidden.
Field/API changes should be handled through Swagger + config convergence first.

2) Special-File Whitelist (Exception Mechanism)

Only the following files (runtime infrastructure without direct OpenAPI equivalents) may be template-based:

Read the full file on GitHub · 225 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.

1mo ago First seen · 225 lines · 2,931 tokens per session scan A 1067f729a25e

Subscribe to this mod's changes

coze-sdk-gen AGENTS.md is an instructions file published in the GitHub repository coze-dev/coze-sdk-gen (4 stars, last pushed 8mo ago), licensed MIT. It adds 2,931 tokens to every session, about $0.0117 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 2026-10-02.

Building agents Languages

coze-sdk-gen AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
coze-sdk-gen AGENTS.mdcoze-dev/coze-sdk-gen	Instructions file	4	8mo ago	MIT	A	2,931	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

coze-sdk-gen: Instructions file for Codex