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.
curl -O https://raw.githubusercontent.com/Txpple/fvtt-mcp-molten5e/main/.claude/skills/journal-builder/SKILL.mdgit clone --depth 1 https://github.com/Txpple/fvtt-mcp-molten5eWrote 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/skills/txpple/fvtt-mcp-molten5e/journal-builder)<a href="https://agentmods.dev/skills/txpple/fvtt-mcp-molten5e/journal-builder"><img src="https://agentmods.dev/badge/skills/txpple/fvtt-mcp-molten5e/journal-builder/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/skills/txpple/fvtt-mcp-molten5e/journal-builder"><img src="https://agentmods.dev/badge/skills/txpple/fvtt-mcp-molten5e/journal-builder.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 | $0.00232 | $0.02658 |
| Opus 5 | $0.00116 | $0.01329 |
| Sonnet 5 | $0.00046 | $0.00532 |
| Haiku 4.5 | $0.00023 | $0.00266 |
Grade A, and why
journal-builder 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Journal builder
The judgment + prose layer for the written side of an adventure (design.md §5): handouts, lore, read-aloud (boxed) text, quest logs, GM notes — and the §8 landing zone for session recaps / campaign logs. This is the deliberate inverse of the old behaviour, where the tool fabricated quest prose (read-aloud, NPC dialogue, hooks). Now you write the words; the tools only structure + style them.
The line that matters — yours vs the tool's
- You (this skill) write every WORD — the read-aloud boxed text, the lore, the quest hook, the GM guidance, the handout copy. Authoring that narrative prose IS the job.
- The tool only STRUCTURES — it renders your typed blocks into the
.mcp-journalhouse style, sets per-page visibility (player vs GM), and inserts real document links. It never writes a word.
Authoring policy — what compendium-first means HERE
Read _shared/authoring-policy.md (2024 · compendium-first · never
SRD · ask-don't-invent). One journal-specific clarification:
- Compendium-first / ask-don't-invent govern the game CONTENT a journal REFERENCES — the monster in the ambush, the magic item in the reward, the spell on the trap. Point at the real compendium / world documents (mix-and-match) and @UUID-link them; never invent their stats.
- They do NOT constrain the GM's narrative prose — the story, the boxed text, the lore — which is yours to author. That's the whole point of this skill.
- Still don't fabricate canon you weren't given — a new region, a named NPC, a plot turn the user didn't ask for. Offer it as a suggestion or STOP and ASK; don't silently invent setting facts.
Tools
create-quest-journal— the STRUCTURING creator (your main tool). Takespages: [{ name, playerVisible?, blocks[] }]→ renders each page's blocks into the house style. Despite the name it builds ANY structured journal (handout, lore, notes), not just quests.update-quest-journal— append a new styled section (fromblocks) to a page, or start a new page (newPageName). The progress-log / §8 session-recap path.link-quest-to-npc— insert a real@UUID[Actor.id]{Name}link to a world NPC, labelled byrelationship(questGiver / target / ally / enemy / contact). Refuses an unknown NPC (no dead links).create-journal/update-journal— generic pages: raw HTML content (+ per-pageplayerVisible). Use when you already have HTML, or want a plain page with no house style. Acreate-journalpage can also be an image page —{name, kind:"image", src, caption?}— so a mixed text+image or image-only journal (e.g. a map-key pack) builds in one call (setsortto order).add-journal-image— append an image page (a map, a handout picture) to an EXISTING journal, with an optionalcaptionandplayerVisible(expose it as a handout; default GM-only).list-journals/search-journals— find/read existing journals + their page ids (needed to targetpageIdfor updates/links).
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 · 149 lines · 232 tokens per session scan A 07b1622a35d5
journal-builder is a skill published in the GitHub repository Txpple/fvtt-mcp-molten5e (0 stars, last pushed today), licensed MIT. It adds 232 tokens to every session and 2,658 once invoked, about $0.0012 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 skills, from other repositories
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
playtest-report
Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.