claude-plugins-community is a read-only mirror of a marketplace listing community-contributed plugins for Claude Cowork and Claude Code. It is for discovering and installing plugins that extend those Claude products, while submissions are handled through Anthropic’s separate review process. Catalogue add-ons represent plugins, skills, and integrations associated with this marketplace.
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 anthropics/claude-plugins-community --skill html-plangit clone --depth 1 https://github.com/anthropics/claude-plugins-communityWrote 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/anthropics/claude-plugins-community/html-plan)<a href="https://agentmods.dev/skills/anthropics/claude-plugins-community/html-plan"><img src="https://agentmods.dev/badge/skills/anthropics/claude-plugins-community/html-plan/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/anthropics/claude-plugins-community/html-plan"><img src="https://agentmods.dev/badge/skills/anthropics/claude-plugins-community/html-plan.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 | $0.00091 | $0.03038 |
| Opus 5.5 | $0.00036 | $0.01215 |
| Sonnet 5.5 | $0.00018 | $0.00608 |
| Haiku 4.5 | $0.00009 | $0.00304 |
Grade A, and why
html-plan 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
html-plan
Plan this: $ARGUMENTS
You write one HTML file by hand. It holds a tree of claims. A small runtime draws the tree and lets the reader open it level by level, answer decisions, edit schemas, comment on anything, and copy one response back to you. Do not start building until that response arrives.
<this skill's directory>/
runtime/htmlplan.css htmlplan.js ← link both from the page; pack inlines them
runtime/pack.mjs ← lint + inline → one portable file (needs only node)
references/blocks.md ← every block, with syntax. Read it before you write.
examples/scheduled-send.html ← a full plan. Copy its shape.
The tree
Each level answers one question. The question picks the exhibit.
| Level | Answers | The claim is | Exhibit |
|---|---|---|---|
h1 |
What is this? | a title: the change and the place, 3 to 7 words | none |
details.thread |
Why? | — | the user's own words, as closed quotes |
| 1 | What can someone now do or see? | a behaviour | doc-mock; doc-machine if it has a lifecycle |
| 2 | How does that work? | one entrypoint, rule or record | doc-calls, doc-schema, or short doc-code |
| 3 | Where? | file:line |
doc-code |
<!doctype html>
<html lang="en">
<meta charset="utf-8">
<title>Scheduled Send Plan</title> <!-- a name: 2–4 words -->
<link rel="stylesheet" href="htmlplan.css"> <!-- pack finds the files by name; use the real path to runtime/ to preview unpacked -->
<script src="htmlplan.js" defer></script>
<body>
<header>
<h1>Scheduling Sent Messages in PostBox</h1> <!-- a title, not a sentence. No label line above it -->
<doc-changes new="5" changed="4"></doc-changes> <!-- files the plan will add, change or delete; drawn as "Proposed · 9 files +5 new ~4 changed" -->
<details class="thread"><summary>Why · 2 requests</summary> …doc-quote… </details> <!-- WHY: the user's own words -->
</header>
<main>
<doc-plan>
<doc-claim> <!-- 1 · WHAT -->
<p>The user can pick a time in the composer.</p> <!-- first child: the claim -->
<doc-mock frame="none" w="440">…</doc-mock> <!-- then ONE exhibit -->
<doc-claim> <!-- 1.1 · HOW -->
<p>“Send later” saves the message with a time. It does not send.</p>
<doc-calls …>…</doc-calls>
<doc-claim at="server/src/scheduled/routes.ts:18"> <!-- 1.1.1 · WHERE; at= matches a call row's @ path:line -->
<p><b>routes.ts:18</b> · createScheduled()</p>
<doc-code …>…</doc-code>
</doc-claim>
</doc-claim>
<doc-claim>
<p>A user can hold 50 scheduled messages at most.</p>
<doc-code …>…</doc-code>
<doc-ask id="limit">…</doc-ask> <!-- a decision sits on the claim it changes -->
</doc-claim>
</doc-claim>
<doc-claim aux="shared"><p>Shared: one new table.</p><doc-schema lang="sql" …>…</doc-schema></doc-claim>
<doc-claim aux="scope"><p>Not changing: normal send, drafts, the mail provider.</p><ul>…</ul></doc-claim>
</doc-plan>
</main>
</body></html>
What ships with it
5 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 · 175 lines · 91 tokens per session scan A ac5dd7da4f7f
html-plan is a skill published in the GitHub repository anthropics/claude-plugins-community (4,688 stars, last pushed yesterday), licensed Apache-2.0. It adds 91 tokens to every session and 3,038 once invoked, about $0.0004 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 2026-10-06.
Other skills, from other repositories
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…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…