cassini-workshop: Command for Claude Code

.claude/commands/git-remote.md

git-remote is a command for Claude Code from opagani/cassini-workshop. It costs 28 tokens per session (1,718 once invoked), scanned A, a copy of git-remote, MIT.

A command for creating a GitHub home for an existing project, including its remote repository, license, README, contribution guide, security guide, and issue templates.

In plain words
What is it for?
Use it to choose a repository name and visibility, add project documentation, set a license, and prepare the first GitHub push.
Why use it?
It turns an unprepared project into a clearer, more complete public or private repository and checks important setup choices first.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: model in frontmatter; mentions CLAUDE.md; names the AskUserQuestion tool.

This is opagani/cassini-workshop's own configuration. It tells Claude Code how to work on cassini-workshop 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 cassini-workshop configures →

Reuse

Borrowing it

Nothing to install: this file belongs to opagani/cassini-workshop. 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/opagani/cassini-workshop/main/.claude/commands/git-remote.md
Clone the repo
git clone --depth 1 https://github.com/opagani/cassini-workshop

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 git-remote

README.md
[![agentmods](https://agentmods.dev/badge/commands/opagani/cassini-workshop/git-remote/github.svg)](https://agentmods.dev/commands/opagani/cassini-workshop/git-remote)
Your own site
<a href="https://agentmods.dev/commands/opagani/cassini-workshop/git-remote"><img src="https://agentmods.dev/badge/commands/opagani/cassini-workshop/git-remote/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 git-remote

Your own site · 80×15
<a href="https://agentmods.dev/commands/opagani/cassini-workshop/git-remote"><img src="https://agentmods.dev/badge/commands/opagani/cassini-workshop/git-remote.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,718 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00028 $0.01718
Opus 5.5 $0.00011 $0.00687
Sonnet 5.5 $0.00006 $0.00344
Haiku 4.5 $0.00003 $0.00172

Measured 2mo ago against content hash 50341ffba673, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

git-remote 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.

Origin

This is a copy

100% identical to git-remote — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/git-remote.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

git-remote

Stand up the GitHub remote for this project and treat it like a calling card. A scrappy first-push leaves a scrappy first impression. Don't ship a stub. Use the github skill for any commit / PR work along the way.

Preflight

  1. Refuse if a remote already exists. git remote -v — if origin is set and points at github.com, stop and tell the user. Suggest gh repo view or gh repo edit.
  2. gh auth status — refuse if not logged in. Tell the user to run gh auth login.
  3. Read context: CLAUDE.md, docs/PROJECT.md, existing README.md, any LICENSE, CONTRIBUTING.md, SECURITY.md, .github/ — never overwrite without consent.

Interview (ask in one batch)

Use AskUserQuestion to settle the choices that need a human:

  1. Repo name — propose one derived from the project (CLAUDE.md / PROJECT.md), kebab-case, short. Offer 2–3 options.
  2. Visibility — public, private. Default: public (it's a calling card).
  3. License — propose one with a one-line rationale each:
    • MIT — most permissive, easiest to adopt (Recommended for libs/tools).
    • Apache-2.0 — same permissions + explicit patent grant; good for anything corporates will touch.
    • AGPL-3.0 — strong copyleft; use when you want network-use modifications shared back.
    • MPL-2.0 — file-level copyleft; middle ground.
    • Unlicense / CC0 — public domain dedication. Recommend based on project type (CLI/lib → MIT; service/SaaS-y → Apache-2.0; opinionated stack you want kept open → AGPL).
  4. Owner — personal account vs an org (only ask if gh auth status shows the user belongs to orgs).

Calling-card requirements (the bar)

The repo gets pushed only after all of these are in place:

README.md — must be real, never boilerplate

A boilerplate README is anything matching:

  • Just the project name and a one-liner.
  • Contains TODO, Lorem ipsum, "your project here", or the literal scaffold text (e.g. the /init stub TODO — one-line description.).
  • No installation, no usage, no example.
  • Auto-generated create-foo-app content untouched.

Read the full file on GitHub · 201 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. 2mo ago First seen · 201 lines · 28 tokens per session scan A 50341ffba673

Subscribe to this mod's changes

git-remote is a command published in the GitHub repository opagani/cassini-workshop (0 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 1,718 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to git-remote, differing in 0 lines, and is treated as a copy.