sdk: Command for Claude Code

.claude/commands/deploy-prod.md

deploy-prod is a command for Claude Code from WaniWani-AI/sdk. It costs 15 tokens per session (794 once invoked), scanned A, original, MIT.

A command for creating a production deployment pull request from main to deploy/prod with automatic date-based versioning.

In plain words
What is it for?
It checks repository status and branch freshness, finds commits to deploy, calculates the next YYYY-MM-DD-rN version, and prepares the release description.
Why use it?
It provides a repeatable release checklist so outdated branches, missing changes, or duplicate daily release numbers are caught before deployment.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is WaniWani-AI/sdk's own configuration. It tells Claude Code how to work on sdk 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 sdk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to WaniWani-AI/sdk. 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/WaniWani-AI/sdk/main/.claude/commands/deploy-prod.md
Clone the repo
git clone --depth 1 https://github.com/WaniWani-AI/sdk

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 deploy-prod

README.md
[![agentmods](https://agentmods.dev/badge/commands/waniwani-ai/sdk/deploy-prod.svg)](https://agentmods.dev/commands/waniwani-ai/sdk/deploy-prod)
Your own site
<a href="https://agentmods.dev/commands/waniwani-ai/sdk/deploy-prod"><img src="https://agentmods.dev/badge/commands/waniwani-ai/sdk/deploy-prod.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 794 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 5.1 $0.00015 $0.00794
Opus 5 $0.00008 $0.00397
Sonnet 5 $0.00003 $0.00159
Haiku 4.5 $0.00002 $0.00079

Measured 6d ago against content hash c95b5e14d32b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

deploy-prod 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 6d 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.

.claude/commands/deploy-prod.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a production deployment pull request following these steps:

Pre-flight Checks

  1. Check working directory is clean

    git status --porcelain
    

    If not clean, warn the user and stop.

  2. Fetch latest from origin

    git fetch origin
    
  3. Check if main is up to date with origin/main

    git rev-parse main
    git rev-parse origin/main
    

    If they differ, warn the user that local main is not up to date.

  4. Check if there are changes to deploy

    git log origin/deploy/prod..origin/main --oneline
    

    If no commits, inform the user there's nothing new to deploy.

Determine Version

  1. Get today's date in format YYYY-MM-DD

  2. Check existing tags for today

    git tag -l "YYYY-MM-DD-r*"
    
  3. Calculate next release number

    • If no tags for today exist, use r1
    • If YYYY-MM-DD-r1 exists, use r2, etc.
  4. Format version: YYYY-MM-DD-r{N} (e.g., 2026-01-19-r1)

  5. Get latest release tag for the compare link

    git tag -l "*-r*" --sort=-version:refname | head -1
    

Gather Changes for PR Description

  1. Get commits between deploy/prod and main

    git log origin/deploy/prod..origin/main --oneline
    
  2. Filter to only include commits with GitHub PR links

    • Only include commits that contain a PR reference like (#123) or (https://github.com/.../pull/123)
    • Exclude commits without PR links (these are likely bad merges that should have been squashed)
    • Format each included commit as a bullet point with the PR link

    Example of what to include:

    - feat: add user dashboard (#142)
    - fix: resolve authentication bug (#138)
    

    Example of what to EXCLUDE (no PR link):

    - fix typo
    - refactor: clean up code
    - Merge branch 'feature-x'
    

Create Pull Request

  1. Create PR from main to deploy/prod
    • Use the latest release tag (from step 5 above) in the compare link, e.g., https://github.com/{REPO}/compare/{LATEST_TAG}...main
    • In the "Changes included" section, only list commits that have a GitHub PR link
    gh pr create \
      --base deploy/prod \
      --head main \
      --title "deploy: {VERSION}" \
      --body "$(cat <<'EOF'
    ## Production Release: {VERSION}
    
    ### Changes included
    {LIST_OF_COMMITS_WITH_PR_LINKS_ONLY}
    
    ### Compare
    https://github.com/{REPO}/compare/{LATEST_TAG}...main
    
    ---
    *After merging, a git tag `{VERSION}` will be automatically created.*
    EOF
    )"
    

Read the full file on GitHub · 110 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. 6d ago First seen · 110 lines · 15 tokens per session scan A c95b5e14d32b

Subscribe to this mod's changes

deploy-prod is a command published in the GitHub repository WaniWani-AI/sdk (17 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 794 once invoked, about $0.0001 per session on Opus 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.