sdk: Skill for Claude Code

.agents/skills/deploy-prod/SKILL.md

deploy-prod is a skill for Claude Code, Codex from WaniWani-AI/sdk. It costs 79 tokens per session (913 once invoked), scanned A, original, MIT.

A release workflow for opening a production deployment pull request from the main branch to a deploy/prod branch. A pull request is a proposed code change for review before merging.

In plain words
What is it for?
It checks the working tree and branches, gathers commits for the release, selects the next YYYY-MM-DD-rN version, and prepares the production pull request.
Why use it?
It reduces release mistakes by checking repository state, confirming there are changes to ship, and calculating a date-based release version.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is WaniWani-AI/sdk's own configuration. It tells Claude Code and Codex 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/.agents/skills/deploy-prod/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/WaniWani-AI/sdk

Made for: Claude Code, Codex.

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/skills/waniwani-ai/sdk/deploy-prod.svg)](https://agentmods.dev/skills/waniwani-ai/sdk/deploy-prod)
Your own site
<a href="https://agentmods.dev/skills/waniwani-ai/sdk/deploy-prod"><img src="https://agentmods.dev/badge/skills/waniwani-ai/sdk/deploy-prod.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 913 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00079 $0.00913
Opus 5 $0.00039 $0.00456
Sonnet 5 $0.00016 $0.00183
Haiku 4.5 $0.00008 $0.00091

Measured 8d ago against content hash 6b78beec1d1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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/skills/deploy-prod/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Production Deployment PR

Create a production deployment pull request following these steps.

This skill assumes the repo deploys via a long-lived deploy/prod branch and a GitHub Action that tags deploy/prod on merge. If the repo doesn't use that flow, stop and tell the user.

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):

Read the full file on GitHub · 125 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. 8d ago First seen · 125 lines · 79 tokens per session scan A 6b78beec1d1c

Subscribe to this mod's changes

deploy-prod is a skill published in the GitHub repository WaniWani-AI/sdk (17 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 913 once invoked, about $0.0004 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.