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 ai-authored-content-coherencegit 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/ai-authored-content-coherence)<a href="https://agentmods.dev/skills/rondorkerin/gamestack/ai-authored-content-coherence"><img src="https://agentmods.dev/badge/skills/rondorkerin/gamestack/ai-authored-content-coherence/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/ai-authored-content-coherence"><img src="https://agentmods.dev/badge/skills/rondorkerin/gamestack/ai-authored-content-coherence.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 | $0.00152 | $0.00748 |
| Opus 5 | $0.00076 | $0.00374 |
| Sonnet 5 | $0.00030 | $0.00150 |
| Haiku 4.5 | $0.00015 | $0.00075 |
Grade A, and why
ai-authored-content-coherence 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 12d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-Authored Content Coherence
How to keep content an AI or procedural engine generates coherent at scale — one voice, no retcons, figures and events that cohere into arcs rather than dissolving into interchangeable mush. This is the crux discipline for a headless / AI-authored game, and it is the least solved — treat its rules as engineering hypotheses to de-risk early, not settled law.
When to use this
- Designing the generation pipeline for lore, history, NPCs, items, quests
- Writing the voice spec / style corpus and the machine-readable lore bible
- Building the self-review / coherence pass over generated batches
- Diagnosing generated content that feels samey, contradicts itself, or drifts in voice
Scope
This skill owns coherence of generated content (mostly non-visual). Adjacent siblings:
- The generator itself + the sameness problem →
procedural-generation - The review pass that gates a batch →
procgen-review(this skill's self-review pass is that gate) - Visual coherence / house style (the visual analogue) →
art-direction-and-readability - The lore the bible encodes →
worldbuilding-and-lore - Quests generated over world state →
narrative-and-quest-design
How the pieces fit
GUIDE.md— the why, with exemplars and citations. Heavily flagged: this topic's verification phase largely failed (session limit), so nearly all rules are sourced but unverified. The sources themselves are strong (Compton; Grinblat & Bucklew / Caves of Qud; LLM-consistency papers).CHECKLIST.md— the what to do: Do/Don't plus "Test for" criteria for a generator, a corpus, and a self-review pass.
The one idea to anchor on
Mathematical uniqueness is not perceived variety. A generator can emit endless mathematically-distinct artifacts that players still read as one undifferentiated mass (the "10,000 bowls of oatmeal"). Coherence-at-scale is won by a shared voice + a never-violate fact bible + recurring thematic domains + an explicit self-review pass — and even then, coherence at full open-world scale is unsolved. De-risk with the oatmeal/fanfic tests from day one.
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.
- 12d ago First seen · 38 lines · 152 tokens per session scan A 565a08ec5609
ai-authored-content-coherence is a skill published in the GitHub repository rondorkerin/gamestack (28 stars, last pushed 2mo ago), licensed MIT. It adds 152 tokens to every session and 748 once invoked, about $0.0008 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
ux-design
Guided, section-by-section UX spec authoring for a screen, flow, or HUD. Reads game concept, player journey, and relevant GDDs to provide context-aware design guidance. Produces ux-spec.md (per screen/flow) or hud-design.md using the studio templates.
architecture-review
Validates completeness and consistency of the project architecture against all GDDs. Builds a traceability matrix mapping every GDD technical requirement to ADRs, identifies coverage gaps, detects cross-ADR conflicts, verifies engine compatibility consistency across all decisions, and produces a PASS/CONCERNS/FAIL…
localize
Full localization pipeline: scan for hardcoded strings, extract and manage string tables, validate translations, generate translator briefings, run cultural/sensitivity review, manage VO localization, test RTL/platform requirements, enforce string freeze, and report coverage.
vertical-slice
Pre-Production validation — build a production-quality end-to-end build to confirm the full game loop is achievable before committing to Production. Run after GDDs, architecture, and UX specs are complete. Produces a PROCEED/PIVOT/KILL verdict that gates the Pre-Production → Production transition.
quick-design
Lightweight design spec for small changes — tuning adjustments, minor mechanics, balance tweaks. Skips full GDD authoring when a system GDD already exists or the change is too small to warrant one. Produces a Quick Design Spec that embeds directly into story files.
soak-test
Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.