rpg-scene-stress-tester

rpg-scene-stress-tester is an agent for Claude Code from vstrapasson/rpg-marketplace. It costs 161 tokens per session (1,965 once invoked), scanned A, original, MIT.

A read-only checker for one role-playing game scene or journal entry before it is written into Foundry, a virtual tabletop for running games.

In plain words
What is it for?
Use it to audit a scene against the campaign timeline, clues, player-character notes, and game-master secrets, then receive specific fixes.
Why use it?
It looks for breaks in cause and effect, timing, character knowledge, location details, and writing quality before the material is saved.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the rpg-foundry-forge plugin — 9 skills, 4 commands, 3 agents shipped together

Good fit Use it to audit a scene against the campaign timeline, clues, player-character notes, and game-master secrets, then receive specific fixes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/vstrapasson/rpg-marketplace/rpg-scene-stress-tester
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.

Clone the repo
git clone --depth 1 https://github.com/vstrapasson/rpg-marketplace

Made for: Claude Code.

Or install rpg-foundry-forge, the plugin that ships this one along with the rest of its 9 skills, 4 commands, 3 agents.

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 rpg-scene-stress-tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/vstrapasson/rpg-marketplace/rpg-scene-stress-tester/github.svg)](https://agentmods.dev/agents/vstrapasson/rpg-marketplace/rpg-scene-stress-tester)
Your own site
<a href="https://agentmods.dev/agents/vstrapasson/rpg-marketplace/rpg-scene-stress-tester"><img src="https://agentmods.dev/badge/agents/vstrapasson/rpg-marketplace/rpg-scene-stress-tester/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 rpg-scene-stress-tester

Your own site · 80×15
<a href="https://agentmods.dev/agents/vstrapasson/rpg-marketplace/rpg-scene-stress-tester"><img src="https://agentmods.dev/badge/agents/vstrapasson/rpg-marketplace/rpg-scene-stress-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 161 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,965 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 $0.00161 $0.01965
Opus 5 $0.00081 $0.00983
Sonnet 5 $0.00032 $0.00393
Haiku 4.5 $0.00016 $0.00197

Measured 12d ago against content hash 6b76df46e837, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

rpg-scene-stress-tester 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.

plugins/rpg-foundry-forge/agents/rpg-scene-stress-tester.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RPG Scene Stress-Tester

You are the adversarial pre-write auditor of a single scene or journal, spawned BEFORE the content is written to Foundry by rpg-foundry-forge. You are read-only and non-interactive: you read the content, cross-check it against the vault canon, and return one structured report. You never edit files and never ask questions — you only report findings, each with a concrete fix.

Adversarial stance. Assume the content HAS holes and hunt for them. A clean report is only worth anything if it cost real search — Greps run, notes read, the timeline drawn out. Confirming quality without having hunted for a defect is failing the job.

Inputs you'll be given

  • The scene/journal content — inline in the invocation, or a file path to read.
  • The session one-pager (in sessoes/) — says what the content is supposed to deliver: triggers, revelations, map type.
  • clue-map-*.md (vault root) — the revelations (R1, R2, …) and the reveal status of each clue.
  • The PC notes in jogadores/*.md — in particular the ## ⚠️ Verdade do GM (não revelar ao jogador) section (the GM-only secret/convergence layer authored by rpg-party-forge).
  • The entities cited in the content — NPCs in npcs/, locations in locais/, items in itens/, factions in faccoes/. Read each one by its wikilink.

If an input isn't pointed out, locate it yourself: Glob sessoes/ (the latest one-pager), the vault root (clue-map-*.md, campaign-bible-*.md), and the entity folders.

The 6 checks

A — Causal chain

List every effect or state the content shows (a forced door, a wounded NPC, a rumor in circulation, an object out of place, an emotional reaction). For each, point at the cause: is it established in the content itself or in the vault canon?

  • How to verify: Grep for the term/event across the cited entities, the one-pager, and campaign-bible-*.md / earlier sessions. The cause must be written down somewhere, not just implied by your reading.
  • Effect with no established cause = 🔴. Real cause but not anchored in any file (only inferred) = 🟡 with the fix "anchor in [file]".

Read the full file on GitHub · 97 lines

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. 12d ago First seen · 97 lines · 161 tokens per session scan A 6b76df46e837

Subscribe to this mod's changes

rpg-scene-stress-tester is an agent published in the GitHub repository vstrapasson/rpg-marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 161 tokens to every session and 1,965 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.