fvtt-mcp-molten5e: Skill for Claude Code

.claude/skills/plot-drift-check/SKILL.md

plot-drift-check is a skill for Claude Code from Txpple/fvtt-mcp-molten5e. It costs 199 tokens per session (1,645 once invoked), scanned A, original, MIT.

A skill that compares a live Foundry campaign world with its authoritative plot document. Foundry is a virtual tabletop for running role-playing games.

In plain words
What is it for?
Auditing campaign journals, roll tables, and other world content, then reporting mismatches for approval before any fixes.
Why use it?
It finds plot drift, such as old names, contradictory text, dropped story elements, or private story information shown to players.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is Txpple/fvtt-mcp-molten5e's own configuration. It tells Claude Code how to work on fvtt-mcp-molten5e itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fvtt-mcp-molten5e configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Txpple/fvtt-mcp-molten5e. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Txpple/fvtt-mcp-molten5e/main/.claude/skills/plot-drift-check/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Txpple/fvtt-mcp-molten5e

Made for: Claude Code.

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 plot-drift-check

README.md
[![agentmods](https://agentmods.dev/badge/skills/txpple/fvtt-mcp-molten5e/plot-drift-check/github.svg)](https://agentmods.dev/skills/txpple/fvtt-mcp-molten5e/plot-drift-check)
Your own site
<a href="https://agentmods.dev/skills/txpple/fvtt-mcp-molten5e/plot-drift-check"><img src="https://agentmods.dev/badge/skills/txpple/fvtt-mcp-molten5e/plot-drift-check/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 plot-drift-check

Your own site · 80×15
<a href="https://agentmods.dev/skills/txpple/fvtt-mcp-molten5e/plot-drift-check"><img src="https://agentmods.dev/badge/skills/txpple/fvtt-mcp-molten5e/plot-drift-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 199 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,645 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 $0.00199 $0.01645
Opus 5 $0.00100 $0.00822
Sonnet 5 $0.00040 $0.00329
Haiku 4.5 $0.00020 $0.00164

Measured 8d ago against content hash e498eb3049a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

plot-drift-check 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 8d 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.

.claude/skills/plot-drift-check/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plot-drift check

A campaign's plot doc and its Foundry world drift apart: a renamed NPC survives in a roll-table entry, an old description lingers in a journal, a dropped subplot still has a quest giver. This skill diffs the two and reports every mismatch. The tools own the reads and the surgical writes; this skill owns what counts as canon, what counts as drift, and what is deliberate.

Report first, fix second. The default deliverable is a drift report. Never edit anything until the user approves findings — then fix each with the narrowest tool available.

Step 1 — establish canon

  1. Get the current plot document. Look in the campaign's notes repo first: if the user keeps a per-campaign repo (a campaign pointer memory names it), its plot/ directory holds the authoritative doc — the newest draft there is canon. Only ask the user for a path if no campaign repo or pointer exists. Read the file itself — never work from a memory summary or condensed plot reference; the whole point is that summaries and worlds go stale.
  2. Extract the canon terms, in four buckets:
    • Named entities — NPCs, factions, places, artifacts/relics, deities, quest names.
    • Renames — anything the doc marks as renamed/superseded, PLUS ask the user: "any renames or retcons since the last pass?" A rename's OLD name is the highest-value search term in the whole audit.
    • Checkable facts — who gives which quest, where an item is, physical descriptions, counts ("four ruins"), relationships. Only facts the world could plausibly contradict.
    • Secrets — canon the players must not see yet (twists, true identities, endings).
  3. For each term, derive the search stem: the shortest distinctive form ("Sleeper" catches "Sleeper's" and "the Sleeper"; avoid stems that collide with common words).

Step 2 — sweep the world

Sweep broadest-text-first; every hit gets recorded with its document type, name, id, and the offending snippet.

Read the full file on GitHub · 109 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. 8d ago First seen · 109 lines · 199 tokens per session scan A e498eb3049a4

Subscribe to this mod's changes

plot-drift-check is a skill published in the GitHub repository Txpple/fvtt-mcp-molten5e (0 stars, last pushed 7d ago), licensed MIT. It adds 199 tokens to every session and 1,645 once invoked, about $0.0010 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.