rpg-foundry-forge-help

rpg-foundry-forge-help is a command for Claude Code from vstrapasson/rpg-marketplace. It costs 20 tokens per session (813 once invoked), scanned A, original, MIT.

A command for compiling a checked Obsidian vault into a playable Foundry VTT game session. Foundry VTT is software for running tabletop role-playing games online.

In plain words
What is it for?
Use it to build a full game night, combat encounter, or non-combat challenge with tokens, lighting, player ownership, journals, and roll or progress tracking.
Why use it?
It turns prepared and validated game material into scenes, actors, journals, and encounters while exposing missing information instead of making it up.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

Good fit Use it to build a full game night, combat encounter, or non-combat challenge with tokens, lighting, player ownership, journals, and roll or progress tracking.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/vstrapasson/rpg-marketplace/rpg-foundry-forge-help
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-foundry-forge-help

README.md
[![agentmods](https://agentmods.dev/badge/commands/vstrapasson/rpg-marketplace/rpg-foundry-forge-help/github.svg)](https://agentmods.dev/commands/vstrapasson/rpg-marketplace/rpg-foundry-forge-help)
Your own site
<a href="https://agentmods.dev/commands/vstrapasson/rpg-marketplace/rpg-foundry-forge-help"><img src="https://agentmods.dev/badge/commands/vstrapasson/rpg-marketplace/rpg-foundry-forge-help/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-foundry-forge-help

Your own site · 80×15
<a href="https://agentmods.dev/commands/vstrapasson/rpg-marketplace/rpg-foundry-forge-help"><img src="https://agentmods.dev/badge/commands/vstrapasson/rpg-marketplace/rpg-foundry-forge-help.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 813 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 $0.00020 $0.00813
Opus 5 $0.00010 $0.00407
Sonnet 5 $0.00004 $0.00163
Haiku 4.5 $0.00002 $0.00081

Measured 9d ago against content hash 88944eeb7a44, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

rpg-foundry-forge-help 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 9d 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/commands/rpg-foundry-forge-help.md · 33 lines

What it actually says

rpg-foundry-forge — help

Present this conversationally.

What it is. The realization layer of the RPG marketplace: it compiles a validated Obsidian vault (built by loremaster/gamemaster, validated by the guardian) into a playable Foundry VTT session, driving the foundry-vtt-mcp server. It compiles — it does not author. Missing data is surfaced, never invented.

Compile units: a sessao (a whole game night), an encontro (one combat), or a desafio (one non-combat challenge — social/chase/research/infiltration). Acts/whole-campaign are future.

What it builds: scenes + mood lighting · creature actors placed as tokens with correct disposition (+ optional AI token art) · quest/lore journals + a campaign dashboard (optional Paizo theme via rpg-journal-forge/references/paizo-theme.md) · player ownership · assembled encounters · non-combat challenges (challenge journal + DCs + live request-player-rolls + a VP progress clock).

Quality gates (per-artifact). Narrative journals are vetted before writing by rpg-scene-stress-tester (causal chain, timeline, who-knows-what per NPC and per PC against the clue map + the PCs' GM-secret layer, space physics, prose) — a Blocker stops the write. After writing, rpg-journal-verifier fetches the journal back via MCP and checks theme classes, enrichers, language, verbatim snippets, and folder. rpg-foundry-reviewer still audits the whole session at the review step.

Also (on demand, not a compile unit): rpg-treasure-forge syncs party wealth — it reads each PC's actual Foundry inventory + currency (get-character/search-character-items), reconciles the ## Wealth section of the party overview (the kit's first vault sync-back), and pushes awarded loot onto the PCs' sheets (add-to-actor, approval-gated). Ask for it with "sync the party's wealth" / "push the loot to the sheets".

Prerequisites:

  • foundry-vtt-mcp registered, and the Foundry MCP Bridge module connected (reload the world / /mcp reconnect after a restart).
  • For full features: the local MCP patches (update-token imagePath, the scene-geometry tools) and ComfyUI (:8000) for map/token-art generation. Missing optionals degrade gracefully — preflight tells you what will be skipped.

Commands:

  • /forge-preflight — check all dependencies (go/no-go) before building.
  • /forge-compile <note> — compile a sessao, encontro, or desafio: preflight → resolve → dry-run plan (you approve) → build → verify → review.
  • /forge-status — what's built vs pending for the current world.
  • /forge-verify — re-audit the built session against the vault (after manual Foundry edits).

Good to know:

  • Builds are idempotent and resumable via build-manifest-<world>.md in the vault root — re-running skips what's done.
  • It serializes scene writes (a Foundry quirk) and prefers existing scenes/journals by name.
  • Organic-map walls are left to you in Foundry's wall tool — pixel-precise tracing of painted maps isn't reliable to automate. The plugin lights scenes and places tokens; you draw walls where you want dynamic line-of-sight.
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. 9d ago First seen · 33 lines · 20 tokens per session scan A 88944eeb7a44

Subscribe to this mod's changes

rpg-foundry-forge-help is a command published in the GitHub repository vstrapasson/rpg-marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 813 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.