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.
curl -O https://raw.githubusercontent.com/WaniWani-AI/sdk/main/.claude/commands/deploy-prod.mdgit clone --depth 1 https://github.com/WaniWani-AI/sdkWrote 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.
[](https://agentmods.dev/commands/waniwani-ai/sdk/deploy-prod)<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>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.
| Model | Per session | Once 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 |
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.
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
-
Check working directory is clean
git status --porcelainIf not clean, warn the user and stop.
-
Fetch latest from origin
git fetch origin -
Check if main is up to date with origin/main
git rev-parse main git rev-parse origin/mainIf they differ, warn the user that local main is not up to date.
-
Check if there are changes to deploy
git log origin/deploy/prod..origin/main --onelineIf no commits, inform the user there's nothing new to deploy.
Determine Version
-
Get today's date in format
YYYY-MM-DD -
Check existing tags for today
git tag -l "YYYY-MM-DD-r*" -
Calculate next release number
- If no tags for today exist, use
r1 - If
YYYY-MM-DD-r1exists, user2, etc.
- If no tags for today exist, use
-
Format version:
YYYY-MM-DD-r{N}(e.g.,2026-01-19-r1) -
Get latest release tag for the compare link
git tag -l "*-r*" --sort=-version:refname | head -1
Gather Changes for PR Description
-
Get commits between deploy/prod and main
git log origin/deploy/prod..origin/main --oneline -
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' - Only include commits that contain a PR reference like
Create Pull Request
- 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 )" - Use the latest release tag (from step 5 above) in the compare link, e.g.,
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.
- 6d ago First seen · 110 lines · 15 tokens per session scan A c95b5e14d32b
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.
Other commands, from other repositories
release
Prepara e pubblica una nuova release del plugin mcp-legal-it. Bumpa la versione in tutti i manifest, aggiorna i changelog e la description con il conteggio tool corretto, crea il release branch, merge in main e tagga.
ship
Prepare a release — does not publish.
gsd:ship
Create PR, run review, and prepare for merge after verification passes.
gsd:complete-milestone
Archive completed milestone and prepare for next version.
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
ship
Ship is the operational release-prep flow for a connected project repo.