savecraft.gg: Skill for Claude Code

.claude/skills/deploying-to-production/SKILL.md

deploying-to-production is a skill for Claude Code from joshsymonds/savecraft.gg. It costs 83 tokens per session (1,279 once invoked), scanned A, original, Apache-2.0.

A release guide for Savecraft’s independently versioned components. It compares the latest Git tags with actual changes and suggests semantic version increases before production deployment.

In plain words
What is it for?
Use it when deploying, releasing, tagging, shipping, or checking which Savecraft components need a production release.
Why use it?
It helps identify what changed, choose an appropriate version bump, and prepare the exact tags that trigger production releases.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is joshsymonds/savecraft.gg's own configuration. It tells Claude Code how to work on savecraft.gg 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 savecraft.gg configures →

Reuse

Borrowing it

Nothing to install: this file belongs to joshsymonds/savecraft.gg. 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/joshsymonds/savecraft.gg/main/.claude/skills/deploying-to-production/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/joshsymonds/savecraft.gg

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 deploying-to-production

README.md
[![agentmods](https://agentmods.dev/badge/skills/joshsymonds/savecraft.gg/deploying-to-production/github.svg)](https://agentmods.dev/skills/joshsymonds/savecraft.gg/deploying-to-production)
Your own site
<a href="https://agentmods.dev/skills/joshsymonds/savecraft.gg/deploying-to-production"><img src="https://agentmods.dev/badge/skills/joshsymonds/savecraft.gg/deploying-to-production/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 deploying-to-production

Your own site · 80×15
<a href="https://agentmods.dev/skills/joshsymonds/savecraft.gg/deploying-to-production"><img src="https://agentmods.dev/badge/skills/joshsymonds/savecraft.gg/deploying-to-production.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,279 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00083 $0.01279
Opus 5 $0.00042 $0.00639
Sonnet 5 $0.00017 $0.00256
Haiku 4.5 $0.00008 $0.00128

Measured 10d ago against content hash 6332e4547932, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

deploying-to-production scanned grade A with 1 finding 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/propose-releases.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| Install | `install-v` | `deploy-install.yml` | Install Worker + curl script to R2 |
.claude/skills/deploying-to-production/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploying to Production

Savecraft has independently versioned components. Each has its own tag prefix, deploy workflow, and relevant paths. Production deploys are triggered by pushing a semver tag.

Step 1: Run the proposal script

Always start by running the script. Do not attempt to find tags or diff history manually.

bash .claude/skills/deploying-to-production/scripts/propose-releases.sh

The script handles tag discovery, path filtering, and net-diff calculation. It only shows components with actual changes (not commits that touched-then-reverted a path).

Step 2: Interpret the output

For each component with changes, review the commits and diff stat. Present a summary table:

Component Current Tag Proposed Tag Reason
cloud cloud-v1.X.Y cloud-v1.X+1.0 ...

Version bump rules

  • Minor (X.Y.0 → X.Y+1.0): New features, UI changes visible to users, new MCP tools, new sections, schema migrations, new plugin capabilities
  • Patch (X.Y.Z → X.Y.Z+1): Bug fixes, lint fixes, formatting, dependency bumps, copy changes, test-only changes
  • When in doubt, prefer minor

Step 3: Confirm and tag

After the user approves, provide the exact git commands:

git tag <tag> && git push origin <tag>

Each tag push triggers its deploy workflow automatically via GitHub Actions.

Component → Deploy Workflow Map

Component Tag Prefix Workflow What Deploys
Daemon daemon-v deploy-daemon.yml Go binaries (Linux/macOS/Windows), MSI, R2 upload, GitHub Release
Cloud cloud-v deploy-cloud.yml Worker (API/MCP/DOs) + Web (Pages) + Site (Pages) + D1 migrations
Install install-v deploy-install.yml Install Worker + curl script to R2
Plugin plugin-{game}-v deploy-plugin.yml WASM parser + manifest + icon to R2

Critical: Reference Module Deploy Targets

Reference modules have split deploy targets depending on their type:

Read the full file on GitHub · 97 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 97 lines · 83 tokens per session scan A 6332e4547932

Subscribe to this mod's changes

deploying-to-production is a skill published in the GitHub repository joshsymonds/savecraft.gg (12 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,279 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.