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.
npx skills add lttr/claude-marketplace --skill update-pluginsgit clone --depth 1 https://github.com/lttr/claude-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/skills/lttr/claude-marketplace/update-plugins)<a href="https://agentmods.dev/skills/lttr/claude-marketplace/update-plugins"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/update-plugins/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/skills/lttr/claude-marketplace/update-plugins"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/update-plugins.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 | $0.00063 | $0.00768 |
| Opus 5.5 | $0.00025 | $0.00307 |
| Sonnet 5.5 | $0.00013 | $0.00154 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
update-plugins 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 13d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update plugins
Every plugin install is recorded in ~/.claude/plugins/installed_plugins.json with its scope and, for local and project scope, its project folder. Each install stays on its own version until it is updated from that folder, so claude plugin update in one repo leaves the others behind. The user usually doesn't know what is outdated where. Find out, recommend, and ask before changing anything.
Prerequisites
bash3.2 or newer (macOS default is fine; on Windows, Git Bash),jq,git
Workflow
-
Run the read-only check:
${CLAUDE_SKILL_DIR}/scripts/check-plugins.shIt prints two tab-separated tables:
# marketplaces: name, last update date, and whether the local clone isup to date,behind remote,remote unreachableornot a git clone.# installs: status, scope, plugin, installed version, latest version in the local clone, project folder. Statuses:outdated,current,dir missing,latest unknown,not in marketplace,ahead of clone.
-
Report, most useful first:
- Marketplaces behind remote. "Latest" comes from the local clone, so recommend refreshing these first; it may reveal more updates.
- Outdated installs, grouped by scope (user, then local, then project), and within a scope by plugin with version jump and folder count. Name the folders only when there are few.
- Stale records (
dir missing) andnot in marketplace(plugin removed or renamed upstream), as one short line each. These can't be updated. - Skip
currententirely.
-
Ask what to do with numbered options, e.g. refresh marketplaces, update everything outdated, only user scope, only one plugin. Recommend one. Do nothing until the user answers.
-
Do what the user picked:
- Refresh marketplaces:
claude plugin marketplace update <name>for each chosen one. There is a single clone per marketplace whatever scope declared it, so this changes the catalog for every project. Then rerun the check and report newly outdated installs before updating anything. - Update installs: pipe the chosen rows from the check into the update script, selecting with
awkon status, scope, plugin or project:
- Refresh marketplaces:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 51 lines · 63 tokens per session scan A 591a4b9a1422
update-plugins is a skill published in the GitHub repository lttr/claude-marketplace (2 stars, last pushed 14d ago), licensed MIT. It adds 63 tokens to every session and 768 once invoked, about $0.0003 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 2026-10-07.
Other skills, from other repositories
lakefs-versioning
Use when lakeFS data versioning — Git-like branching for data lakes, atomic commits, time travel, CI/CD. Use when working with lakefs versioning.
git-worktree-workspaces
Sets up and uses Git worktrees for parallel task workspaces in the same repository clone, including safe cleanup of local worktrees. Invoked when the user asks to work on multiple branches at once, isolate tasks without extra clones, or create/remove worktrees.
excalidraw
Create Excalidraw diagrams programmatically. Use when the user wants architecture diagrams, flowcharts, or any visual diagram with a hand-drawn aesthetic, where editable output and drag-and-drop editing add value over Mermaid's text-only approach.
ia
Evaluate and improve how information is organized for findability. Use when the user asks to "organize this", "restructure docs", "improve navigation", "where should this go", "review file structure", or when documentation grows beyond a single page.
naming
Evaluate and improve names in code using naming as a design diagnostic. Use when the user asks to "name this", "rename", "review naming", "what should I call", struggles to name something, or when a code review surfaces vague or misleading names.
testing
Design test strategy using Beck's Test Desiderata — which properties matter, which tradeoffs to make. Use when the user asks "how should I test this", "what tests do I need", "review my test strategy", "is this well-tested", or when planning tests for a new feature or refactor.