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-scene-stress-tester)<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.
<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>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 | $0.00161 | $0.01965 |
| Opus 5 | $0.00081 | $0.00983 |
| Sonnet 5 | $0.00032 | $0.00393 |
| Haiku 4.5 | $0.00016 | $0.00197 |
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.
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 byrpg-party-forge). - The entities cited in the content — NPCs in
npcs/, locations inlocais/, items initens/, factions infaccoes/. 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]".
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 · 97 lines · 161 tokens per session scan A 6b76df46e837
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.
Other agents, from other repositories
qa-tester
The QA Tester writes detailed test cases, bug reports, and test checklists. Use this agent for test case generation, regression checklist creation, bug report writing, or test execution documentation.
player
Runtime verification teammate for one code task. Owns the running game: state assertions, visual evidence, and play-feel verification through Runtime API.
reviewer
VibeGame build final quality gate. Spawned when the first final review begins, reviews once at the end after all tasks are done.
godot-tools-engineer
Use this agent for Godot 4.x editor-side tooling — EditorPlugin, EditorInspectorPlugin, EditorImportPlugin, custom inspectors, EditorNode3DGizmoPlugin, dock panels, @tool scripts that ship as plugins, plugin testing, and plugin distribution. Works in both GDScript and C# (with #if TOOLS guards). GDExtension (C++…
playtester
You are a brutally honest game tester for SYNTH. You don't sugarcoat. You find problems.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.