prefab-authoring

prefab-authoring is a skill for Claude Code, Codex from vucinatim/air-jam. It costs 35 tokens per session (404 once invoked), scanned A, original, MIT.

Rules for defining reusable gameplay objects and scene presets in Air Jam. A prefab is a reusable description of an object, such as a pickup, obstacle or prop, with its settings and behavior kept clearly separated.

In plain words
What is it for?
Use it when creating pickups, obstacles, props, spawnable entities or reusable scene content with stable metadata and configurable defaults.
Why use it?
It keeps reusable content easy to inspect, configure, preview and create consistently without hiding large amounts of game logic inside it.

Skill for Claude CodeCodex

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

Good fit Use it when creating pickups, obstacles, props, spawnable entities or reusable scene content with stable metadata and configurable defaults.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vucinatim/air-jam/prefab-authoring
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 vucinatim/air-jam --skill prefab-authoring
Clone the repo
git clone --depth 1 https://github.com/vucinatim/air-jam

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 prefab-authoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/vucinatim/air-jam/prefab-authoring/github.svg)](https://agentmods.dev/skills/vucinatim/air-jam/prefab-authoring)
Your own site
<a href="https://agentmods.dev/skills/vucinatim/air-jam/prefab-authoring"><img src="https://agentmods.dev/badge/skills/vucinatim/air-jam/prefab-authoring/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 prefab-authoring

Your own site · 80×15
<a href="https://agentmods.dev/skills/vucinatim/air-jam/prefab-authoring"><img src="https://agentmods.dev/badge/skills/vucinatim/air-jam/prefab-authoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 404 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.
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 $0.00035 $0.00404
Opus 5 $0.00017 $0.00202
Sonnet 5 $0.00007 $0.00081
Haiku 4.5 $0.00003 $0.00040

Measured 10d ago against content hash b34029a64ac4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

prefab-authoring 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 10d 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.

packages/cli/template-assets/bootstrap/skills/prefab-authoring/SKILL.md · 49 lines

What it actually says

Prefab Authoring

Use this skill when adding reusable scene objects, pickups, obstacles, props, spawnable entities, or authored content presets.

Read First

  1. docs/airjam/prefab-authoring.md
  2. docs/airjam/generated/project-structure.md
  3. docs/airjam/generated/state-and-rendering.md if the prefab introduces hot runtime behavior

Contract Rule

A prefab should be a reusable content unit, not a hidden pile of gameplay logic.

Keep the prefab definition declarative and stable enough that future tooling can:

  1. scan it
  2. render a preview
  3. expose safe config
  4. instantiate it consistently

Structure Rules

  1. place prefab code under src/game/prefabs/
  2. keep metadata, schema, and runtime component clearly separated
  3. put pure behavior in domain/system modules when it outgrows the prefab itself
  4. avoid coupling prefab definitions directly to scene-global mutable state
  5. keep scene-population, spawn, and pooling layers outside src/game/prefabs/

Config Rules

  1. expose explicit defaults
  2. keep config serializable where practical
  3. use stable ids, labels, categories, and tags
  4. avoid hidden magic props or implicit scene dependencies

Anti-Patterns

  1. one-off scene objects masquerading as reusable prefabs
  2. prefab files that bury behavior, metadata, and config in one component
  3. prefab placement rules that depend on trial-and-error offsets
  4. prefab contracts that are too ad hoc for future scanning or preview generation
  5. plural runtime mappers like Ships or Collectibles living in src/game/prefabs/ when they are actually population layers over state
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 · 49 lines · 35 tokens per session scan A b34029a64ac4

Subscribe to this mod's changes

prefab-authoring is a skill published in the GitHub repository vucinatim/air-jam (6 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 404 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories