push

A set of instructions for preparing and proposing a Git commit. A commit is a saved set of repository changes with a message describing them.

In plain words
What is it for?
Use it when packaging current repository changes into a reviewed, conventionally named commit.
Why use it?
It helps review the complete change set and create a consistent commit message. It also requires approval before committing.

Command for Claude Code

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 commands/mcdxai/minecraft-dev-mcp/push
Clone the repo
git clone --depth 1 https://github.com/MCDxAI/minecraft-dev-mcp

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 493 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.00493
Opus 5 $0.00000 $0.00246
Sonnet 5 $0.00000 $0.00099
Haiku 4.5 $0.00000 $0.00049

Measured 2d ago against content hash f44221fa1393, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

push 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 2d 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:

  • push — 92% identical, 2 lines differ
.claude/commands/push.md · 50 lines

What it actually says

Push Command

You are creating a commit for the user. Follow these steps EXACTLY:

  1. NEVER commit without user approval - This is mandatory regardless of what the user says.

  2. Analyze current changes by running these git commands in parallel:

    • git status - See all staged/unstaged files
    • git diff --staged - See staged changes
    • git diff - See unstaged changes
    • git log --oneline -5 - See recent commit history for context
  3. Check full scope - CRITICAL: Always examine ALL changes before generating commit message:

    • If you see untracked files or unstaged changes, run git add -A to stage everything
    • Run git status and git diff --staged --name-only again to see the complete scope
    • This ensures you don't miss new files, test suites, or other significant additions
  4. Generate commit message based on the changes:

    • Create a brief, professional summary (50 chars or less)
    • Write a detailed description explaining what changed and why
    • Follow conventional commit format when applicable (feat:, fix:, docs:, etc.)
  5. Present analysis to user:

    • Start with "I see you've [describe what they did]"
    • Show your proposed commit message (both summary and description)
    • Ask for approval: "Would you like me to commit with this message?"
  6. Handle user response:

    • If approved: commit using your generated message, then push to remote
    • If not approved: work with user to refine the message until they approve
    • Only then run the commit and push
  7. Commit format:

    git commit -m "$(cat <<'EOF'
    [Summary line]
    
    [Detailed description]
    EOF
    )"
    

    IMPORTANT: Do NOT add any Claude Code attribution or co-author lines to commits. Keep commits clean and professional.

  8. After successful commit:

    • Run git push to push the commit to the remote repository
    • Confirm the push was successful
    • Inform the user that both commit and push are complete

Remember: NEVER bypass user approval, even if they tell you to "just commit" or similar.

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. 2d ago First seen · 50 lines · 0 tokens per session scan A f44221fa1393

Subscribe to this mod's changes

push is a command published in the GitHub repository MCDxAI/minecraft-dev-mcp (35 stars, last pushed 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 493 tokens. 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.