gum-packaging

gum-packaging is a skill for Claude Code, Codex from vchelaru/FlatRedBall2. It costs 82 tokens per session (1,949 once invoked), scanned A, original, MIT.

A tool guide for packaging a Gum game project into one .gumpkg archive containing its project data and referenced assets. Gum is a UI and content tool for games; the archive uses tar and Brotli compression.

In plain words
What is it for?
Use it when preparing a built game for distribution, especially a web or BlazorGL build, and when configuring runtime loading of the bundled content.
Why use it?
It reduces a deployed game's many loose content files to one runtime bundle, which can simplify distribution and web loading. Development should continue with loose files.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when preparing a built game for distribution, especially a web or BlazorGL build, and when configuring runtime loading of the bundled content.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vchelaru/flatredball2/gum-packaging
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.

Any agent
npx skills add vchelaru/FlatRedBall2 --skill gum-packaging
Clone the repo
git clone --depth 1 https://github.com/vchelaru/FlatRedBall2

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 gum-packaging

README.md
[![agentmods](https://agentmods.dev/badge/skills/vchelaru/flatredball2/gum-packaging.svg)](https://agentmods.dev/skills/vchelaru/flatredball2/gum-packaging)
Your own site
<a href="https://agentmods.dev/skills/vchelaru/flatredball2/gum-packaging"><img src="https://agentmods.dev/badge/skills/vchelaru/flatredball2/gum-packaging.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,949 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Prompt Injection · line 82
    Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
    Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 $0.00082 $0.01949
Opus 5 $0.00041 $0.00975
Sonnet 5 $0.00016 $0.00390
Haiku 4.5 $0.00008 $0.00195

Measured 2d ago against content hash db902c08c784, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

gum-packaging 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.

frb-skills/gum-packaging/SKILL.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gum Packaging (.gumpkg)

gumcli pack walks a Gum project's dependencies and writes a single tar+brotli bundle (.gumpkg) containing the elements, font cache, and external textures. The project can be either of Gum's two on-disk formats — XML (.gumx/.gusx/.gucx/.gutx/.behx) or JSON (.gumj/.gusj/.gucj/.gutj/.behj, converted from XML via gumcli convert-to-json) — pack and runtime bundle loading both resolve dependencies against whichever family the project actually is. At runtime, Gum picks loose vs. bundle from the extension of the path you pass.gumx/.gumj load loose, .gumpkg loads the bundle. There is no sibling probing: the extension is the single source of truth (a probe would be a guaranteed-404 HTTP request on Blazor/WASM). So the path your code passes must match the artifact your build deployed.

When to use

  • Shipping a build — fewer files to copy, faster startup on web targets, no static-asset manifest bloat.
  • BlazorGL/WASM specifically — many small .gusx/.gucx/.png files are slow to fetch over HTTP; one .gumpkg is one request.
  • Don't pack during authoring — the Gum editor saves loose files. Keep loose during development; pack for distribution.

Pack command

Run from the project directory that contains the .gumx:

"$GUMCLI" pack Content/GumProject/GumProject.gumx

Default output is GumProject.gumpkg next to the .gumx. Override with -o:

"$GUMCLI" pack Content/GumProject/GumProject.gumx -o build/GumProject.gumpkg

gumcli is the GumCli .NET tool — dotnet tool install -g GumCli, or pin it in a local .config/dotnet-tools.json and invoke via dotnet gumcli (preferred in a build, so the tool version tracks the Gum NuGet version). See the gumcli skill.

Categories (--include)

Default is core,fontcache,external — everything. Trim if your build pipeline regenerates pieces:

  • core — the project + element files (.gumx+.gusx/.gucx/.gutx/.behx, or the JSON equivalents)
  • fontcache — generated .fnt/.png under FontCache/
  • external — sprite-source .pngs and custom fonts referenced by the project but living outside Core/FontCache. This includes a Font value that's a project-relative .ttf path (not just CustomFontFile) — Gum detects it from the .ttf extension alone, no registration needed. Requires Gum/KernSmith 2026.8.28.1-preview.1+ — on an older Gum, pack still writes the file into the bundle but the runtime can't read it back out, so text silently falls back to KernSmith's embedded placeholder font instead of erroring.

Read the full file on GitHub · 135 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. 2d ago First seen · 135 lines · 82 tokens per session scan A db902c08c784

Subscribe to this mod's changes

gum-packaging is a skill published in the GitHub repository vchelaru/FlatRedBall2 (14 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 1,949 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 2026-09-04.