What is chatgpt-cli AGENTS.md?

Repository instructions for working on chatgpt-cli, a Go command-line program. They explain where commands, application logic, provider APIs, agent behavior, configuration, tests, and documentation live, plus how to build and test.

Use them when changing command-line behavior, internal logic, provider integrations, agent features, configuration, or tests, and when choosing the project’s Makefile-based workflow.

They give an agent a map of the codebase and reduce mistakes such as changing the wrong package or skipping the project’s required checks.

How kardolus/chatgpt-cli configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to kardolus/chatgpt-cli. 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/kardolus/chatgpt-cli/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/kardolus/chatgpt-cli

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/kardolus/chatgpt-cli/agents-md/github.svg)](https://agentmods.dev/instructions/kardolus/chatgpt-cli/agents-md)

Your own site

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

Per session 1,317 This file is loaded in full into every session.

When invoked 1,317 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	$0.01317	$0.01317
Opus 5.5	$0.00527	$0.00527
Sonnet 5.5	$0.00263	$0.00263
Haiku 4.5	$0.00132	$0.00132

Measured 2mo ago against content hash 1dc57a7ae0fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chatgpt-cli 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 · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Operating guide for automated agents (and humans) working in this repository.

This repo is a Go-based CLI application (module: github.com/kardolus/chatgpt-cli) built with Cobra (commands) and Viper (configuration). Agent mode and policies live under agent/.

Use this document as the default working context: how to navigate the repo, how to make changes safely, and what “done” means.

1) Repo map (where things usually live)

cmd/ — CLI commands, flags, wiring (Cobra).
internal/ — core application logic (non-exported).
api/ — API clients + domain/types for providers.
agent/ — agent runtime: planning, tools, budgets, policy.
config/ — config defaults/templates.
docs/ — documentation.
scripts/ — repo workflows used by Make targets.
test/ — tests + fixtures (including MCP test servers).
vendor/ — vendored dependencies (do not edit by hand).

Rule of thumb:

If it changes user-facing flags/output: start in cmd/.
If it changes behavior/business logic: it likely belongs in internal/, api/, or agent/.

2) Build & test workflow (use Makefile first)

Prefer Make targets over ad-hoc commands; the scripts encode the intended workflow.

List targets:

make help

“Done” means tests pass:

make unit
make integration

Do not skip integration tests unless explicitly instructed.

Other useful targets:

make all-tests (tests + lint/format/tidy)
make contract
make smoke
make coverage
make install / make reinstall / make binaries
make updatedeps

Notes:

Run go mod tidy only when dependency changes are intended.
Never edit vendor/ directly; use the dependency workflow (make updatedeps).

3) Go version

Go version is defined in go.mod. Avoid using language/library features newer than that version unless the module version is intentionally bumped.

4) Testing expectations (required)

For any behavior change or new feature, add or update tests.

Read the full file on GitHub · 176 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 · 176 lines · 1,317 tokens per session scan A 1dc57a7ae0fc

Subscribe to this mod's changes

chatgpt-cli AGENTS.md is an instructions file published in the GitHub repository kardolus/chatgpt-cli (965 stars, last pushed 1mo ago), licensed MIT. It adds 1,317 tokens to every session, about $0.0053 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.

Go Languages Productivity Testing chatgpt cli go gpt language-model

chatgpt-cli AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
chatgpt-cli AGENTS.mdkardolus/chatgpt-cli	Instructions file	965	1mo ago	MIT	A	1,317	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	today	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

chatgpt-cli: Instructions file for Codex