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.
npx skills add rondorkerin/gamestack --skill procedural-generationgit clone --depth 1 https://github.com/rondorkerin/gamestackWrote 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/skills/rondorkerin/gamestack/procedural-generation)<a href="https://agentmods.dev/skills/rondorkerin/gamestack/procedural-generation"><img src="https://agentmods.dev/badge/skills/rondorkerin/gamestack/procedural-generation/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.
<a href="https://agentmods.dev/skills/rondorkerin/gamestack/procedural-generation"><img src="https://agentmods.dev/badge/skills/rondorkerin/gamestack/procedural-generation.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00134 | $0.00524 |
| Opus 5 | $0.00067 | $0.00262 |
| Sonnet 5 | $0.00027 | $0.00105 |
| Haiku 4.5 | $0.00013 | $0.00052 |
Grade A, and why
procedural-generation 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 9d 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.
What it actually says
Procedural Generation
How to make generators whose output is perceptually rich, not just mathematically infinite — the central skill for a headless, AI-authored game.
When to use this
- Designing any generator (terrain, dungeons, quests, items, NPCs, lore, history)
- Diagnosing generated content that reads as samey / generic / soulless
- Deciding the handcrafted-vs-procedural ratio
- Setting up an AI authoring engine that needs one coherent voice
Scope
This is the how to generate knowledge skill. Its companion is procgen-review — the process skill that gates generated output against these principles (oatmeal test, fanfic test, sameness scan). Generate with this; review with that.
Related: open-world-design (generating space), worldbuilding-and-lore + ai-authored-content-coherence (generating lore coherently), systemic-emergent-design (multiplicative systems).
How the pieces fit
GUIDE.md— the why: the oatmeal problem, perceptual uniqueness, the hybrid model, corpus voice, intentionality/local logic, multiplicative systems, curated randomness, apophenia. Cited.CHECKLIST.md— the what to do: Do/Don't + test-for criteria.
The one idea to anchor on
Perceptual uniqueness is the only metric that matters. You can generate 10,000 mathematically-unique bowls of oatmeal; the player still just sees oatmeal (Kate Compton). Intentionality — constraints, handcrafted anchors, local meaning, and a single voice — is what separates great procedural content from infinite filler.
Start with GUIDE.md; gate everything you generate with procgen-review.
What ships with it
2 files 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.
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.
- 9d ago First seen · 33 lines · 134 tokens per session scan A ebb5d57d33b8
procedural-generation is a skill published in the GitHub repository rondorkerin/gamestack (27 stars, last pushed 2mo ago), licensed MIT. It adds 134 tokens to every session and 524 once invoked, about $0.0007 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 skills, from other repositories
consistency-check
Scan all GDDs against the entity registry to detect cross-document inconsistencies: same entity with different stats, same item with different values, same formula with different variables. Grep-first approach — reads registry then targets only conflicting GDD sections rather than full document reads.
debug-issue
Systematic Godot debugging decision trees for physics, signals, rendering, navigation, and input issues.
asset-audit
Audits game assets for compliance with naming conventions, file size budgets, format standards, and pipeline requirements. Identifies orphaned assets, missing references, and standard violations.
cgs-bug-report
Use for bug report tasks that capture a reproducible bug with environment, steps, expected/actual behavior, severity, evidence, and owner; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-bug-triage
Use for bug triage tasks that classify bugs by severity, priority, reproduction confidence, owner role, risk, and release impact; produce verification evidence, changed or proposed files, and handoff boundaries.
cgs-bugfix
Use for bugfix tasks that fix a bounded bug with reproduction evidence, minimal change, regression coverage, and handoff notes; produce verification evidence, changed or proposed files, and handoff boundaries.