groove-admin-update

groove-admin-update is a skill for Claude Code from andreadellacorte/groove. It costs 18 tokens per session (1,318 once invoked), scanned A, original, MIT.

A maintenance workflow for updating local Groove skills after a new GitHub release. Groove is a repository and local state system whose installed version is recorded in .groove/index.md.

In plain words
What is it for?
Use it to fetch the latest release, apply pending migrations in order, update the recorded version after each successful step, and report whether the installation is current.
Why use it?
It prevents local skill files and migration state from falling behind the latest published release or being marked up to date incorrectly.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; names the AskUserQuestion tool; mentions AGENTS.md.

Good fit Use it to fetch the latest release, apply pending migrations in order, update the recorded version after each successful step, and report whether the installation is current.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/andreadellacorte/groove/groove-admin-update
Install

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.

Any agent
npx skills add andreadellacorte/groove --skill groove-admin-update
Clone the repo
git clone --depth 1 https://github.com/andreadellacorte/groove

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 groove-admin-update

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/andreadellacorte/groove/groove-admin-update"><img src="https://agentmods.dev/badge/skills/andreadellacorte/groove/groove-admin-update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,318 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. Third-party audits
  • Socket warn 23 Mar 2026
  • Snyk warn 23 Mar 2026
How audits are shown
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 $0.00018 $0.01318
Opus 5 $0.00009 $0.00659
Sonnet 5 $0.00004 $0.00264
Haiku 4.5 $0.00002 $0.00132

Measured 8d ago against content hash 87e464dbc1c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

groove-admin-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 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.

skills/groove-admin-update/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

groove-admin-update

Maintainers (andreadellacorte/groove repo): After publishing a new GitHub Release, run this from the groove repo root so checked-in .agents/skills/groove* matches what npx skills add andreadellacorte/groove installs — see CONTRIBUTING.md (“Publish release”). Do not use manual rsync from skills/ for that.

Outcome

All pending migrations are applied to the user's local groove state in version order. .groove/index.md reflects the current installed groove version.

Acceptance Criteria

  • groove-version: in .groove/index.md matches version: in skills/groove/SKILL.md after update
  • Each pending migration was applied in order
  • groove-version: updated after each successful migration (partial progress is recoverable)
  • If already up to date, reports clearly and exits
  • Source-of-truth check: "up to date" is only reported when the installed skill version equals the latest GitHub release; if the add step left an older version on disk (e.g. cached or default branch), the user is warned and told how to fix it

Steps

  1. Fetch latest release tag from https://api.github.com/repos/andreadellacorte/groove/releases/latest (tag_name, strip leading v). This is the target version. If the API call fails, skip the version check and continue without a target.
  2. Install with retry: Run npx skills add andreadellacorte/groove --yes (no @tag — the CLI does not support tag syntax). After it completes, read version: from skills/groove/SKILL.md and compare to the target. If the installed version is still older than the target, wait 10 seconds and retry npx skills add andreadellacorte/groove --yes. Repeat up to 3 times total. If all attempts fail to install the target version, report: "Installed v but latest release is v — npx skills add may be caching an older version. Try again later." and exit.
    • After a successful install, re-read this SKILL.md (skills/groove-admin-update/SKILL.md) from disk before continuing — the skill refresh may have updated the update command itself, and the remainder of these steps must reflect the latest version
  3. Read groove-version: from .groove/index.md — if key absent, assume 0.1.0 and write it
  4. Read installed version from version: in skills/groove/SKILL.md (already confirmed to match target in step 2)
  5. If local and installed versions match: report "groove is up to date (v)" and exit
  6. Read skills/groove/migrations/index.md — parse the migration table
  7. Filter rows where To > local version AND To <= installed version, in table order — the From field is informational only and does not gate execution
  8. If no migrations found but versions differ: update groove-version: in .groove/index.md directly to the installed version and report "no state migrations needed — version bumped to v"
  9. For each pending migration: a. Report "Applying → : " b. Read and execute the migration file c. Update groove-version: in .groove/index.md to the To version d. Report "✓ → applied"
  10. Report summary: N migrations applied, now at v
  11. Re-sync platform symlinks after update:
    • For each directory in .agents/skills/ that starts with groove:
      • Ensure .claude/skills/<name> is a symlink → ../../.agents/skills/<name> (create or update if stale)
      • Ensure .cursor/skills/<name> is a symlink → ../../.agents/skills/<name> if .cursor/skills/ exists
    • Remove any .claude/skills/groove-* or .cursor/skills/groove-* entries that no longer exist in .agents/skills/ (stale symlinks from removed skills)
    • Run: for skill in .agents/skills/groove*; do name=$(basename "$skill"); ln -sfn "../../.agents/skills/$name" ".claude/skills/$name"; done
    • Use ln -sfn (no-dereference) to avoid creating nested symlinks inside existing directory symlinks
    • Report: "✓ platform symlinks refreshed"

Read the full file on GitHub · 63 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 · 63 lines · 18 tokens per session scan A 87e464dbc1c0

Subscribe to this mod's changes

groove-admin-update is a skill published in the GitHub repository andreadellacorte/groove (5 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,318 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.

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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens