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/commands/vstrapasson/rpg-marketplace/rpg-vault-guardian-help)<a href="https://agentmods.dev/commands/vstrapasson/rpg-marketplace/rpg-vault-guardian-help"><img src="https://agentmods.dev/badge/commands/vstrapasson/rpg-marketplace/rpg-vault-guardian-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.
<a href="https://agentmods.dev/commands/vstrapasson/rpg-marketplace/rpg-vault-guardian-help"><img src="https://agentmods.dev/badge/commands/vstrapasson/rpg-marketplace/rpg-vault-guardian-help.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 | $0.00026 | $0.01767 |
| Opus 5 | $0.00013 | $0.00883 |
| Sonnet 5 | $0.00005 | $0.00353 |
| Haiku 4.5 | $0.00003 | $0.00177 |
Grade A, and why
rpg-vault-guardian-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 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Present this guide to the user conversationally — walk them through what the plugin is for and the workflows below — then offer to start the workflow that best fits where they are (a brand-new vault, a single edit, or a full audit).
What it is for
You keep your campaign notes in an Obsidian (or plain Markdown) vault, and you want every region, NPC, quest, and lore note to follow a consistent schema with valid frontmatter and unbroken wikilinks. This plugin gives you a single validated write path so bad entities never hit disk, an on-demand audit that finds and fixes schema, link, and coherence problems and rebuilds your indexes, and a one-command scaffolder to lay down the expected folder structure for a brand-new campaign.
Quick start
Launch Claude Code from your campaign vault root — the folder that contains (or will contain) the entity subfolders like regioes/ and npcs/:
cd ~/Documents/obsidian/main && claude
- Brand-new vault? Run
/rpg-initfirst to scaffold the 17 folders. - Existing vault? Just ask Claude to create or edit an entity (e.g. "create an NPC named Sister Avelina") — the write gate engages automatically.
What you can do
| How to invoke | What it does | Reach for it when |
|---|---|---|
/rpg-init |
Scaffolds the campaign's initial 17-folder structure in the current directory, then reports which folders were newly created vs. already existed. | Once, at the very start of a new campaign vault, before you create any entities. |
create an NPC named ... (rpg-preserve) |
The single write point: picks the correct folder for the entity type, builds frontmatter and content, validates in memory, and writes the .md only when there are zero errors — otherwise it lists the offending fields and asks you to fix them. |
Every time you create or edit any of the 15 entity types. The only sanctioned way to write entities to disk. |
audit my campaign (rpg-audit) |
Runs a 7-step audit: snapshot, deterministic validation, safe auto-fixes, LLM health check, confirmed destructive fixes, MOC/index regeneration, final report. | Periodically or after bulk edits, to repair missing frontmatter, broken links, orphans, and wrong-target references and rebuild your maps-of-content. |
have the rpg-guardian audit the vault (agent) |
Runs the full 7-step audit in an isolated subagent context, then returns a structured summary of initial errors, fixes applied, MOC regeneration, and errors remaining. | When you want the complete audit without cluttering your main conversation, or just a clean consistency report. |
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 · 72 lines · 26 tokens per session scan A 9b94010a1007
rpg-vault-guardian-help is a command published in the GitHub repository vstrapasson/rpg-marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,767 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.
Other commands, from other repositories
session-end
I'll summarize this coding session and update the memory system with our accomplishments.
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.