rpg-aplicar-glosas

rpg-aplicar-glosas is a command for Claude Code from vstrapasson/rpg-marketplace. It costs 26 tokens per session (1,122 once invoked), scanned A, original, MIT.

A command that applies pending comments or proposed changes in an RPG campaign vault one at a time through a controlled write process. Each applied item is marked with the commit that recorded it.

In plain words
What is it for?
It is for processing proposed changes to whole notes, passages, or individual fields.
Why use it?
It provides an ordered way to review and apply queued corrections instead of changing campaign notes without tracking them.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the rpg-vault-guardian plugin — 2 skills, 5 commands, 1 agent, 3 hooks shipped together

Good fit It is for processing proposed changes to whole notes, passages, or individual fields.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add vstrapasson/rpg-marketplace
Claude Code
/plugin install rpg-vault-guardian

Made for: Claude Code.

Or install rpg-vault-guardian, the plugin that ships this one along with the rest of its 2 skills, 5 commands, 1 agent, 3 hooks.

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-aplicar-glosas

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/vstrapasson/rpg-marketplace/rpg-aplicar-glosas"><img src="https://agentmods.dev/badge/commands/vstrapasson/rpg-marketplace/rpg-aplicar-glosas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,122 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 $0.00026 $0.01122
Opus 5.5 $0.00010 $0.00449
Sonnet 5.5 $0.00005 $0.00224
Haiku 4.5 $0.00003 $0.00112

Measured 20d ago against content hash 45968d685eab, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rpg-aplicar-glosas 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 20d 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-vault-guardian/commands/rpg-aplicar-glosas.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rpg-aplicar-glosas — Apply the pending Glosas queue

Run against the current vault (CWD must be the vault root). List the pending queue first. If the vault's MCP server is running (the mcp__rpg-vault__list_glosas tool is available in this session), call it instead with { status: "pendente" }: it answers from the server's live index in one call, with the same result. Otherwise, run the script:

node "${CLAUDE_PLUGIN_ROOT}/scripts/glosas.mjs" --vault "$(pwd)" --status pendente

If there are none, tell the GM the queue is empty and stop.

Otherwise work through the pending Glosas one at a time, in the order printed (oldest first). For each one, read its fields:

  • alvo — one or more vault-relative note paths this Glosa concerns.
  • tipo — entidade (a note on the whole Entity), trecho (a note on a quoted passage) or campo (a proposed new value for one field).
  • campo/de/para (only for tipo: campo) — the field and its proposed new value.
  • trecho (only for tipo: trecho) — the exact passage the Glosa points at.
  • comentario — the GM's own words; always read this even when the other fields already say what to change, since it's often the reason, not just the instruction.

1. Apply the change to every target

Edit every note listed in alvo — never only the first — through the normal write path, exactly as you would for any other Entity change:

  • tipo: campo — campo is the note's own frontmatter key (role, status, location, faction, front…): use rpg-preserve's "Updating an existing entity" recipe (a patch merging { [campo]: para } into the existing frontmatter; a link value such as [[O Mercado das Cinzas]] is already written the way the note stores it). Two values of campo are not frontmatter keys:
    • epiteto — the italic epithet line right under the title: replace that line's text (de) with para, through the same recipe's body rewrite.
    • titulo — the note's title. Change its # H1 to para the same way, then tell the GM the file itself still carries the old name: renaming it is the GM's call in Obsidian, which also updates every link to it.
  • tipo: trecho — use the same recipe, replacing the quoted trecho within the body with the corrected text (build the new body yourself; the recipe carries the rest of the body through verbatim).
  • tipo: entidade — use whichever recipe fits the comment: a field patch, a body addition (append), or a body rewrite.

Read the full file on GitHub · 51 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. 20d ago First seen · 51 lines · 26 tokens per session scan A 45968d685eab

Subscribe to this mod's changes

rpg-aplicar-glosas is a command published in the GitHub repository vstrapasson/rpg-marketplace (2 stars, last pushed 20d ago), licensed MIT. It adds 26 tokens to every session and 1,122 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-28.