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/starter-series/create-starter/createnpx skills add starter-series/create-starter --skill creategit clone --depth 1 https://github.com/starter-series/create-starterWhat 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 | $0.00043 | $0.00688 |
| Opus 5 | $0.00022 | $0.00344 |
| Sonnet 5 | $0.00009 | $0.00138 |
| Haiku 4.5 | $0.00004 | $0.00069 |
Grade A, and why
create scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
The `create-starter` MCP server exposes two tools. Use them directly — do **not** shell out to `curl`, `tar`, or `git clone`. How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are scaffolding a new project using the Starter Series templates via the create-starter MCP server.
How to invoke
The create-starter MCP server exposes two tools. Use them directly — do not shell out to curl, tar, or git clone.
list_templates— returns the full template table as JSON.create_project— scaffolds a new project.
Workflow
- Pick a template. If the user named one explicitly, resolve it against the registry below. If not, call
list_templatesand ask the user to pick one. - Collect required input:
name(required) — project name. Must match^[A-Za-z0-9][A-Za-z0-9_-]*$(alnum start, then[A-Za-z0-9_-]only). No dots, no spaces, no path separators.description(optional) — one-line description that replaces the template default.output_dir(optional) — where to create the project. Defaults to./<name>relative to the MCP server's cwd.
- Call
create_projectwith the gathered arguments. The server handles download, extraction, placeholder substitution, Python package renaming, andgit init. - Report the next steps from the tool's response (it returns a
cd-then-install sequence tuned to the template).
Template registry
| ID | Name | Category |
|---|---|---|
mcp-server |
MCP Server (TypeScript) | mcp |
mcp-server-python |
MCP Server (Python) | mcp |
npm-package |
npm Package | package |
discord-bot |
Discord Bot | bot |
telegram-bot |
Telegram Bot | bot |
browser-extension |
Browser Extension (MV3) | extension |
vscode-extension |
VS Code Extension | extension |
electron-app |
Electron App | app |
react-native |
React Native (Expo) | app |
cloudflare-pages |
Cloudflare Pages | deploy |
docker-deploy |
Docker Deploy (language-agnostic) | deploy |
Call list_templates for the authoritative, up-to-date list with full metadata.
Rules
- Never invent template IDs. Only use IDs returned by
list_templatesor present in the table above. - Never construct tarball URLs or shell commands yourself — always go through
create_project. - If the tool returns an
isError: trueresponse, surface the message verbatim and stop; do not retry with a different name unless the user asks. - After a successful scaffold, suggest reviewing
.env.exampleif the output mentions environment variables, and remind the user thatgit inithas already run — they just need to add a remote. - Keep your response concise: one line confirming the template + name, then the next-step commands as a code block.
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.
- yesterday First seen · 50 lines · 43 tokens per session scan A da3d6c94d97d
create is a skill published in the GitHub repository starter-series/create-starter (1 stars, last pushed 14d ago), licensed MIT. It adds 43 tokens to every session and 688 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (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
d3k
Use when the user asks to use d3k, run/dev/test/debug a web project with d3k, or reproduce a browser issue. Own the runtime: reuse or background-start d3k non-interactively, wait for readiness, use its project-stable managed Chrome profile, and inspect unified browser/server evidence.
inline-vis
Emit a sandboxed inline HTML visualization in an assistant message when a workspace .html file should render in-thread. Use after writing or updating a demo/chart/report HTML file the user should see without opening a panel.
seo-coach
Enter a friendly OpenSEO coach mode that explains workflows, recommends next steps, and helps users use agents, web search, scraping, and MCP data effectively.
surf
Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.
temps
Manage, deploy, operate, and instrument applications with Temps. Use this skill whenever the user mentions Temps, @temps-sdk/[email protected], deploying or migrating an app to Temps, projects, environments, services, domains, backups, logs, monitoring, analytics, browser Performance Insights/Core Web Vitals, observability…
deep-x-research
Deep, exhaustive research on a topic across X (Twitter) by driving Grok (x.com/i/grok) through surf. Use when the user wants comprehensive X research on a concept, technique, trend, tool, or creator scene; needs categorized findings with every claim traceable to post URLs; or when a single Grok query is not enough.