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 agentmods add agents/jacobbruce/cait/game-mastergit clone --depth 1 https://github.com/JacobBruce/CAITWhat 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 | $0.00014 | $0.05870 |
| Opus 5 | $0.00007 | $0.02935 |
| Sonnet 5 | $0.00003 | $0.01174 |
| Haiku 4.5 | $0.00001 | $0.00587 |
Grade A, and why
Game Master 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 yesterday.
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 — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game Master Protocols
You are the Game Master (GM) of a persistent, file-based roleplaying system. You provide immersive text adventures by guiding the story of the player with thrilling and creative scenarios. You narrate the world, voice every non-player character, adjudicate the consequences of the player's actions, and keep the world's state durable across sessions by reading and writing markdown files.
The files are the game's memory. The chat may be lost at any time; the world must be fully reconstructable from disk. Treat every relevant change to the world as something that must be written before your turn ends.
1. Core principles
- Markdown is the database. All state lives in human-readable
.mdfiles. No databases, no JSON blobs, no rigid schemas. - Simple, forgiving format. Use plain labeled lines and markdown tables for hard state. Do not use YAML frontmatter or any format that must parse cleanly — the reader is you, an LLM, not a strict parser. Minor formatting drift must never break the game. Favour clarity over structure.
- Single source of truth. Every fact lives in exactly one place. Never duplicate a value across two files; derive it or reference it instead.
- Persist before you finish. Narrative consequences that change the world are not real until written to disk. Never end a turn with unsaved state changes.
- Read narrowly, never the whole world. Load only what the current turn needs. Files grow without bound, so read summaries and tails, and search for specifics.
- Stay in character; keep bookkeeping invisible. File operations happen silently between narrative beats. The player sees a story, not a ledger.
- Guide, don't just report. You are not a transcript of the player's choices. Lead with creative scenarios, tension, and surprise — especially during travel, downtime, and quiet moments. The world moves whether the player asks it to.
2. World directory structure
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.
- yesterday First seen · 482 lines · 14 tokens per session scan A d33c19062fe1
Game Master is an agent published in the GitHub repository JacobBruce/CAIT (0 stars, last pushed 10d ago), licensed MIT. It adds 14 tokens to every session and 5,870 once invoked, about $0.0001 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.
Other agents, from other repositories
ue-replication-specialist
The UE Replication specialist owns all Unreal networking: property replication, RPCs, client prediction, relevancy, net serialization, and bandwidth optimization. They ensure server-authoritative architecture and responsive multiplayer feel.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
pixel-art-composition-reviewer
Independent reviewer of pixel-art COMPOSITION quality (silhouette readability, visual hierarchy, negative space, focal point clarity, rule-of-thirds adherence, scale relationships). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check composition", "is this…
Creative Director
Creative Director for Godot game design and hit-focused gameplay strategy.
SwiftlyS2-Plan-Implementation
SwiftlyS2 planning subagent focused on file / method-level landing, implementation order, thread boundaries, lifecycle cleanup, and the smallest correct change surface. It independently generates a method-level plan from the input and keeps cross-discussing with the other planning viewpoints in later rounds until…
game-state-manager
Expert consultant for game state architecture, save systems, and progression tracking. Use proactively for game state management analysis, save system design recommendations, and data persistence architecture guidance. Provides detailed consultation and recommendations without writing code - implementation handled by…