agentleFS
Sign inStart free
FYClamityDestinyFYClamityDestiny/vetted/skills/update/SKILL.md

update

Skill0 starsChanged 6 days agoMITView on GitHub

Update installed tools (Claude plugins, skills, MCP servers, npm/PyPI packages, Docker images, VS Code extensions, Roblox assets, cloned repos) to their current version, scanning only what changed and warning about bad news (archived, deprecated, ownership change, shutting down, license change). Use for "update my plugins", "is anything outdated", "check my installs", /vetted:update [name|all].

64 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use end, create and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • torarnvSkill

    end

    Wrap up a work session. Updates memory files, logs decisions and lessons, appends to the session log.

    Also in 3 projects that use this

  • MicrosoftSkill

    create

    Also in 4 projects that use this

  • bitwize-music-studioSkill

    tutorial

    Provides interactive guided album creation for new users. Use when the user is new to the plugin or asks for a walkthrough of the album creation process.

    Also in 3 projects that use this

  • MicrosoftSkill

    note

    Use this skill to record progress, partial findings, hypotheses, and page-anchored evidence while investigating a long document. Call Note aggressively — any time you read a page and confirm, narrow, or update your understanding of the user's question. Triggers include "jot that down", "save this finding", "note that page 7 says X", or (more often) implicit internal signals — you just learned something and want it recoverable later. Notes persist in the session and Review can select among them. Never paraphrase notes back from memory; write them as you go.

    Also in 4 projects that use this

  • kv0906Skill

    inbox

    Quick capture mode (with content) or batch processing mode (no content). GTD-style routing of inbox items to proper folders. Use "/inbox thought to capture" or "/inbox" to process.

    Also in 4 projects that use this

  • jholhewresSkill

    backup

    Backup and restore — files, databases, and system backups

    Also in 3 projects that use this

  • +2 more from microsoft

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 62 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read ${CLAUDE_PLUGIN_ROOT}/references/vetting.md and ${CLAUDE_PLUGIN_ROOT}/references/sources.md first.

    line 8
  2. Very specific:

    Use ~/.claude/vetted-log.md plus what's actually installed: claude plugin list, ~/.claude/skills, claude mcp list, and the current …

    line 11
  3. Distinctive:

    Shutting down: search the README, the latest release notes and the 10 newest issues for: sunset, end of life, EOL, shutting down, no longer …

    line 18
  4. Very specific:

    If an update was rated or showed bad news, suggest once: "/vetted:share would warn everyone else using this." Never share without their yes.

    line 30

“Common” is measured: kept by at least 6 in 10 of the 62 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Update

Read ${CLAUDE_PLUGIN_ROOT}/references/vetting.md and ${CLAUDE_PLUGIN_ROOT}/references/sources.md first.

1. Inventory

Use ~/.claude/vetted-log.md plus what's actually installed: claude plugin list, ~/.claude/skills, claude mcp list, and the current project's package.json, requirements*.txt/pyproject.toml, docker-compose*.yml and code --list-extensions --show-versions. Without an argument, check everything; with a name, only that.

2. For each item: what's new

Get the latest version and compare it with the installed one. Skip items that are up to date.

3. Bad-news check (even when there's no update)

  • Archived or deprecated: the GitHub isArchived flag, npm deprecated, a PyPI yanked release, the VS Code "deprecated" tag, a Roblox asset taken down.
  • Shutting down: search the README, the latest release notes and the 10 newest issues for: sunset, end of life, EOL, shutting down, no longer maintained, unmaintained, discontinued, moving to, acquired.
  • Ownership change: a new repo owner or redirect, new npm/PyPI maintainers, or a different publisher since the logged install. This is the classic hijack setup.
  • License change: compare the SPDX ID with the logged one (for example MIT changing to a non-commercial license).
  • Security: advisories and malicious-package listings, from the intel output.

4. Scan only what changed

Run intel on the new version. Download the old and new versions side by side (pinned, from sources.md). Diff them: git diff <old>..<new>, or diff -r on unpacked packages. Run scan.sh on the new version, then read every changed file that touches install scripts, entry points, network calls or hooks. Flag the classic hijack signs: a big new minified file, a new install script, a new dependency nobody asked for, or a patch release that adds network code. Compare the new CAPS: line with the one in the log, and call out every new capability. For remote MCP servers, compare the tool-list hash and warn if the tools changed.

5. Report and apply

Table: Name | Installed → Latest | Changes (one line) | Bad news | Rating. Then ask which to update. Apply only the approved ones, each pinned to the scanned version, and update vetted-log.md (new version, rating, date). Never auto-update a ⛔, and don't let an update quietly lower a rating without saying so.

6. Share

If an update was rated or showed bad news, suggest once: "/vetted:share would warn everyone else using this." Never share without their yes.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free