agentmods.dev

chatgpt-cli CLAUDE.md

chatgpt-cli CLAUDE.md is an instructions file for coding agents from kardolus/chatgpt-cli. It costs 1,279 tokens per session, scanned A, original, MIT.

A release guide for chatgpt-cli, a Go command-line program, covering tests, version tags, compiled downloads, GitHub Releases, and the Homebrew package formula. Homebrew is a package manager that installs and upgrades command-line tools.

In plain words
What is it for?
Use it to check prerequisites, run release tests, build binaries for supported systems, publish a GitHub release, and update the sibling Homebrew repository.
Why use it?
It lays out the coordinated release work across the main repository and its Homebrew tap, reducing the chance that one installation method is left outdated.

Instructions file

not rated 955 2d ago A scan 1,279 tokens original MIT
View the source file kardolus/chatgpt-cli
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/kardolus/chatgpt-cli/claude-md
Clone the repo
git clone --depth 1 https://github.com/kardolus/chatgpt-cli

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 chatgpt-cli CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kardolus/chatgpt-cli/claude-md.svg)](https://agentmods.dev/instructions/kardolus/chatgpt-cli/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kardolus/chatgpt-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/kardolus/chatgpt-cli/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,279 This file is loaded in full into every session.
When invoked 1,279 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.01279 $0.01279
Opus 5 $0.00639 $0.00639
Sonnet 5 $0.00256 $0.00256
Haiku 4.5 $0.00128 $0.00128

Measured 4d ago against content hash d10a7bc18359, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chatgpt-cli CLAUDE.md scanned grade A with 1 finding 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 4d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -sL https://github.com/kardolus/chatgpt-cli/archive/refs/tags/vX.Y.Z.tar.gz | shasum -a 256
CLAUDE.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

chatgpt-cli — release runbook

How to cut and publish a new release. A release touches two repos:

  1. this repo (kardolus/chatgpt-cli) — run the tests, tag, build binaries, and publish a GitHub Release with those binaries attached (the direct-download install method).
  2. the Homebrew tap (kardolus/homebrew-chatgpt-cli) — bump the formula so brew upgrade chatgpt-cli picks up the new version.

Homebrew builds chatgpt from source (the formula points at the tag's source tarball), while the pre-built bin/chatgpt-<os>-<arch> artifacts serve the direct-download install documented in the README (releases/latest/download/chatgpt-<os>-<arch>).

The tap repo is expected as a sibling checkout next to this one (i.e. ../homebrew-chatgpt-cli).

Prerequisites

  • Go (the version in go.mod's go directive; the toolchain auto-downloads if GOTOOLCHAIN=auto).
  • golangci-lint v2 on your PATH. The lint step (golangci-lint run, via .golangci.yml) targets the module's Go version; a v1 golangci-lint (built with an older Go) will refuse to run and the release will abort at the test step.
  • ag (the_silver_searcher) — all-tests.sh uses it to scan for stray TODOs.
  • gh (GitHub CLI, authenticated) — to create the GitHub Release and upload binaries.
  • chatgpt on your PATH — shipit uses the CLI itself to generate the release notes.
  • A sibling ../prompts/ directory containing write_release_notes.md; shipit references it as ../prompts/write_release_notes.md.

1. Cut the release

From this repo, on a clean main that's up to date with origin:

make shipit version=vX.Y.Z message="short release message"

version is the new semver tag (bump from the latest tag). This runs scripts/shipit.sh, which:

  1. Aborts if the working tree has unstaged changes.
  2. scripts/updatedeps.sh — go get -u ./..., go mod vendor, go mod tidy; if anything changed, it auto-commits chore: bump dependencies and pushes.
  3. scripts/all-tests.sh — go mod tidy check, go fmt check, golangci-lint run, a TODO scan, then unit + integration + contract tests.
  4. Release notes — diffs the last tag to HEAD and pipes it through chatgpt + ../prompts/write_release_notes.md, printing the notes to stdout. Copy this output — it's the body for the GitHub Release in step 2. (Tip: tee it, e.g. make shipit ... | tee /tmp/release-notes.md.)
  5. Tags the release (git tag -a vX.Y.Z -m "message") and pushes tags.
  6. scripts/binaries.sh — builds bin/chatgpt-<os>-<arch> for 8 targets (darwin / linux / windows / freebsd across amd64 / arm64 / 386), stamping GitCommit and GitVersion (from git describe) via -ldflags.

Read the full file on GitHub · 100 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. 4d ago First seen · 100 lines · 1,279 tokens per session scan A d10a7bc18359

Subscribe to this mod's changes

chatgpt-cli CLAUDE.md is an instructions file published in the GitHub repository kardolus/chatgpt-cli (955 stars, last pushed 2d ago), licensed MIT. It adds 1,279 tokens to every session, about $0.0064 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Git and workflowGochatgptcligogptlanguage-model
Related

Other instructions, from other repositories

langroid CLAUDE.md

Claude Code instructions for langroid/langroid, covering claude.md, commands, development, testing and linting and type checking.

langroid/langroid · 2,637 tokens

generative-ai-for-beginners AGENTS.md

Instructions for microsoft/generative-ai-for-beginners, covering agents.md, project overview, setup commands, initial repository setup and clone the repository.

microsoft/generative-ai-for-beginners · 2,850 tokens

ollama AGENTS.md

AGENTS.md instructions for ollama/ollama, covering agents.md and building.

ollama/ollama · 91 tokens

awesome-go AGENTS.md

AGENTS.md instructions for avelino/awesome-go, covering awesome-go · llm contribution guide, project snapshot, when modifying the awesome list, coding guidelines and testing & validation.

avelino/awesome-go · 624 tokens

go-micro CLAUDE.md

Claude Code instructions for micro/go-micro, covering claude.md - go micro project guide, project overview, build & test, run all tests and run tests for a specific package.

micro/go-micro · 2,139 tokens

ollama CLAUDE.md

Claude Code instructions for ollama/ollama: See AGENTS.md for the shared agent instructions for this repository.

ollama/ollama · 21 tokens