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 agentmods add skills/a8cteam51/claude-code-plugins/clone-new-sitenpx skills add a8cteam51/claude-code-plugins --skill clone-new-sitegit clone --depth 1 https://github.com/a8cteam51/claude-code-pluginsWrote 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/a8cteam51/claude-code-plugins/clone-new-site)<a href="https://agentmods.dev/skills/a8cteam51/claude-code-plugins/clone-new-site"><img src="https://agentmods.dev/badge/skills/a8cteam51/claude-code-plugins/clone-new-site.svg" alt="Measured on agentmods" 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 | $0.00195 | $0.02067 |
| Opus 5 | $0.00097 | $0.01033 |
| Sonnet 5 | $0.00039 | $0.00413 |
| Haiku 4.5 | $0.00019 | $0.00207 |
Grade C, and why
clone-new-site scanned grade C with 2 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 4d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Do not run `curl`, `unzip`, `rm -rf wp-content`, `git clone`, or `studio site create` outside the script. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Do not run `curl`, `unzip`, `rm -rf wp-content`, `git clone`, or `studio site create` outside the script. How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clone a repo as wp-content into a new Studio site
Trigger when the user wants to set up a new local WordPress site whose wp-content is a cloned GitHub repo, with Studio managing it. If the user already has a working local site and wants to convert its wp-content into a git clone, use the clone-into-existing-site skill instead.
All filesystem mutation, git auth preflight, .gitignore patching, and Studio invocation are delegated to ${CLAUDE_PLUGIN_ROOT}/scripts/scaffold.sh. Never re-implement steps inline; that breaks the repeatability guarantee.
This is the same workflow as the /studio-repo-clone:init slash command, exposed via natural language.
Step 0 — extract the repo from the user's message
The user will reference the repo as one of:
- Full GitHub URL:
https://github.com/owner/repoor.git - SSH URL:
[email protected]:owner/repo.git - Shorthand:
owner/repo
If no repo is identifiable in the user's request, ask once via AskUserQuestion (free-text via "Other"). Do not guess a repo.
Derive the repo name from the URL (used as the suggested project name):
owner/repo→repohttps://github.com/owner/repo(.git)?→repo[email protected]:owner/repo.git→repo
Step 1 — get the project name
The project name is used for both the root folder and the Studio site name, so it must be explicit. ALWAYS ask via AskUserQuestion, even if the user mentioned a name in their message — only skip if they very clearly stated one as the project name (e.g. "set up project FOO using repo X").
AskUserQuestion options:
<repo-name>(recommended)- (Other for custom name)
The chosen name MUST be a valid directory name: lowercase letters, digits, hyphens, underscores. If the user provides something invalid, slugify it (e.g. "My Cool Project" → "my-cool-project") and confirm the slug back.
Step 2 — choose the target directory
Run pwd then basename "$(pwd)" and ls -A "$(pwd)" to detect cwd state.
Also detect the user's effective Studio base directory by inspecting existing Studio sites — Studio has no CLI flag that exposes its install root, so we infer it from studio site list:
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.
- 4d ago First seen · 120 lines · 195 tokens per session scan C 214f719a97e1
clone-new-site is a skill published in the GitHub repository a8cteam51/claude-code-plugins (3 stars, last pushed 7d ago), licensed MIT. It adds 195 tokens to every session and 2,067 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…