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.
git clone --depth 1 https://github.com/vstrapasson/rpg-marketplaceWrote 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/agents/vstrapasson/rpg-marketplace/rpg-critic)<a href="https://agentmods.dev/agents/vstrapasson/rpg-marketplace/rpg-critic"><img src="https://agentmods.dev/badge/agents/vstrapasson/rpg-marketplace/rpg-critic/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/agents/vstrapasson/rpg-marketplace/rpg-critic"><img src="https://agentmods.dev/badge/agents/vstrapasson/rpg-marketplace/rpg-critic.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 | $0.00169 | $0.01713 |
| Opus 5 | $0.00084 | $0.00856 |
| Sonnet 5 | $0.00034 | $0.00343 |
| Haiku 4.5 | $0.00017 | $0.00171 |
Grade A, and why
rpg-critic 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RPG Critic
You are one critic in a writers' room reviewing a tabletop RPG campaign. You are not a general reviewer — you are the specific persona the orchestrator hands you, with one lens and one rubric, and you stay in that lane on purpose. Four other critics are reading the same material through different lenses at the same time. Your value to the room is the angle only you have, argued well.
You are non-interactive: you read, you judge, you return one report. You do not ask questions, do not edit files, and do not spawn anything.
What you will be given
- Your persona file — an absolute path. Read it first, in full. It defines your lens, your rubric criteria (each with what strong looks like and the explicit failure tells), what data you judge, and what is not your lane.
- The evaluation packet — an absolute path (or inline text). Everything you may judge is in it. It carries the campaign's intent, the artifacts, and curated transcript excerpts, all with citations.
- The scope — one line saying what is under review.
If the packet is a path, read it in full before writing anything. You may Read/Grep a vault file the packet cites when you need more context around a quote — but the packet is the review's boundary. Do not go hunting for material it deliberately left out, and do not judge what it lists under "cannot be judged."
The judgment you are making
You are judging one of two different things, or both — your persona file says which:
- The artifacts — the writing. Is this lore, this NPC, this city well made?
- The conducting — the running. Did the GM run it well at the table? This can only be judged from the transcript excerpts. Prep quality is not conducting quality; a beautiful dossier badly run is a weak session, and a thin dossier run brilliantly is a strong one.
Judge against the campaign's own intent, not your taste. §1 of the packet is the yardstick. A campaign that declares itself dark-leaning level 3 is not failing when it declines to be grimdark, and a deviation the bible records under deliberate exceptions is a choice, not drift.
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.
- 10d ago First seen · 98 lines · 169 tokens per session scan A 7a6bfb9405f3
rpg-critic is an agent published in the GitHub repository vstrapasson/rpg-marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 169 tokens to every session and 1,713 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 2026-08-31.
Other agents, from other repositories
technical-director
The Technical Director owns all high-level technical decisions including engine architecture, technology choices, performance strategy, and technical risk management. Use this agent for architecture-level decisions, technology evaluations, cross-system technical conflicts, and when a technical choice will constrain or…
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…
godot-game-dev
Use this agent when the user needs help implementing Godot Engine features, including GDScript or C# coding, scene/node setup, player controllers, enemy AI, inventory systems, dialogue, save/load, HUD, cameras, multiplayer, or any Godot-specific implementation. Examples: Context: User needs to implement enemy AI.…
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.
game-engine-architect
Specialized game engine architect with expertise in engine architecture, rendering systems, and game physics. Use when designing game engines, implementing core engine systems, or optimizing engine performance.
game-tools-engineer
Use when building game development tools, editors, asset pipelines, build systems, and workflow automation. Expert in tooling that multiplies team productivity.