grimoire-update

grimoire-update is a skill for Claude Code from ojCezarFerreira/Grimoire. It costs 48 tokens per session (1,563 once invoked), scanned A, original, MIT.

A maintenance procedure for updating the Grimoire plugin to its newest published version. It checks the installed version, retrieves the latest release information, and explains how to apply the update.

In plain words
What is it for?
Use it to check Grimoire's version, review its changelog, and follow the marketplace update and reload process.
Why use it?
It shows what changed and guides the required update steps without modifying the plugin's installation files.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

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 grimoire plugin — 11 skills shipped together

Good fit Use it to check Grimoire's version, review its changelog, and follow the marketplace update and reload process.

Compare 6 skills 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 ojCezarFerreira/Grimoire
Claude Code
/plugin install grimoire

Made for: Claude Code.

Or install grimoire, the plugin that ships this one along with the rest of its 11 skills.

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 grimoire-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/ojcezarferreira/grimoire/grimoire-update/github.svg)](https://agentmods.dev/skills/ojcezarferreira/grimoire/grimoire-update)
Your own site
<a href="https://agentmods.dev/skills/ojcezarferreira/grimoire/grimoire-update"><img src="https://agentmods.dev/badge/skills/ojcezarferreira/grimoire/grimoire-update/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 grimoire-update

Your own site · 80×15
<a href="https://agentmods.dev/skills/ojcezarferreira/grimoire/grimoire-update"><img src="https://agentmods.dev/badge/skills/ojcezarferreira/grimoire/grimoire-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,563 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 $0.00048 $0.01563
Opus 5 $0.00024 $0.00781
Sonnet 5 $0.00010 $0.00313
Haiku 4.5 $0.00005 $0.00156

Measured 9d ago against content hash d5e87a66e9e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

grimoire-update 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.

skills/grimoire-update/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[Required Reading]

  1. Read ${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json. This is the source of truth for the installed Grimoire version on this machine.
  2. Read ${CLAUDE_PLUGIN_ROOT}/GRIMOIRE-CONVENTIONS.md and load § Skill composition, § IDE-aware review and § User-facing language — Phase 4 below depends on it to decide how the changelog is shown to the user. Other sections of the conventions do not apply to this skill.
  3. If .grimoire/PROJECT.md exists in the project root, read it for project context only (tone, audience). Missing → proceed without it; do not suggest grimoire-init here — this skill is plugin maintenance, not project bootstrapping.

[Objective] Update the Grimoire plugin installed in this Claude Code session to the latest published version. The skill does NOT modify any file inside the plugin install directory (~/.claude/plugins/) — Claude Code owns that. It reads the installed version, compares it to the latest on GitHub, shows the user what changed, and guides them through the two official commands required to apply the update. The skill makes no commits in the consumer project; the only file it may write is the ephemeral changelog draft at .grimoire/bag/drafts/grimoire-update-changelog-<epoch>.md when running in IDE mode, which is removed before the skill ends.

[Phase 1: Read installed version]

  • Open ${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json and extract the version field.
  • Report to the user: Installed Grimoire version: X.Y.Z.
  • If the file is missing or malformed, stop and tell the user the installed plugin manifest is unreadable — they should reinstall Grimoire via /plugin install grimoire@grimoire. Do not proceed.

[Phase 2: Fetch latest version]

  • WebFetch https://raw.githubusercontent.com/ojCezarFerreira/grimoire/main/.claude-plugin/plugin.json.
  • Extract the version field from the response.
  • If the request fails (network, repo moved, 404), stop and tell the user the latest version could not be determined and ask them to retry later. Do not assume the plugin is up to date and do not suggest the update commands.

[Phase 3: Compare versions]

  • Compare the installed version (Phase 1) to the latest version (Phase 2) as strings.
  • If equal: print Grimoire is already up to date (X.Y.Z). Nothing to do. and end the skill. Do not print any commands.
  • If different: continue to Phase 4.

[Phase 4: Show changelog]

  • WebFetch https://raw.githubusercontent.com/ojCezarFerreira/grimoire/main/CHANGELOG.md.
  • Extract every ## [VERSION] — DATE section strictly between the installed version (exclusive) and the latest version (inclusive). For each, include the ### Added / ### Changed / ### Fixed / ### Removed bullets verbatim.
  • If the installed version is older than every section in the file, include all sections.
  • Present the extracted slice for review per § IDE-aware review:
    • IDE detected: create .grimoire/bag/drafts/ if it does not exist, then write the changelog to .grimoire/bag/drafts/grimoire-update-changelog-<epoch>.md so the IDE renders it. Generate <epoch> with date +%s at the moment of writing and memorize the full path — it will be reused in Phase 5 (on rejection) and Phase 8 (on completion). Tell the user in one short line that the changelog is open in the editor.
    • Terminal-only fallback: print the extracted slice to the user inline in markdown — concise, no commentary on top.
  • If the changelog cannot be fetched, print a one-line warning (Changelog not available — proceeding without it.) and continue. Do not abort.

[Phase 5: Pause — authorization]

  • Ask the user: Proceed with the update from X.Y.Z to A.B.C? (yes/no).
  • Wait for an explicit answer. Anything other than an unambiguous yes ends the skill cordially with no further output. If Phase 4 wrote the memorized .grimoire/bag/drafts/grimoire-update-changelog-<epoch>.md (IDE mode), delete that exact path before ending. This is the only chance the user has to cancel before the guidance phases begin.

Read the full file on GitHub · 75 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. 9d ago First seen · 75 lines · 48 tokens per session scan A d5e87a66e9e0

Subscribe to this mod's changes

grimoire-update is a skill published in the GitHub repository ojCezarFerreira/Grimoire (2 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 1,563 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens