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/xx5921/pipecat-mcp-server/initnpx skills add xx5921/pipecat-mcp-server --skill initgit clone --depth 1 https://github.com/xx5921/pipecat-mcp-serverWhat 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 | $0.00013 | $0.01717 |
| Opus 5 | $0.00006 | $0.00859 |
| Sonnet 5 | $0.00003 | $0.00343 |
| Haiku 4.5 | $0.00001 | $0.00172 |
Grade A, and why
init 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 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.
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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffold a new Pipecat project by collecting configuration from the user and running pc init in non-interactive mode.
Arguments
/init [--output <PATH>]
--output(optional): Directory where the project will be created. Defaults to the current directory.
Prerequisites
Check if pc is installed by running pc --version. If not installed, tell the user to install it with uv tool install pipecat-ai-cli and stop.
Discover Available Options
Before asking the user any questions, run pc init --list-options to get the current valid values for all fields. The output is JSON:
{
"bot_type": ["web", "telephony"],
"transports": {
"web": ["daily", "smallwebrtc"],
"telephony": ["twilio", "telnyx", ...]
},
"stt": ["deepgram_stt", "openai_stt", ...],
"llm": ["openai_llm", "anthropic_llm", ...],
"tts": ["cartesia_tts", "elevenlabs_tts", ...],
"realtime": ["openai_realtime", "gemini_live_realtime", ...],
"video": ["heygen_video", "tavus_video", "simli_video"]
}
Use this data to populate the choices in every question below. Do NOT hardcode service lists — always use the values from --list-options.
Configuration Flow
Walk through the following questions to build the project configuration. After collecting all answers, show a summary and run the command.
Choosing the right interaction method:
- AskUserQuestion — Use for questions with a small, fixed set of options (bot type, pipeline mode, client framework, yes/no questions). This gives a clean clickable UI.
- Show list as text — Use for questions with many options (STT, LLM, TTS, realtime, video, transports). Display the full list of available options from
--list-optionsformatted as a readable list, then let the user reply with their choice in chat.
Step 1: Project Name
Ask the user for a project name. This will be used as the directory name and project identifier.
Step 2: Bot Type
Ask the user to choose a bot type:
- Web/Mobile (
web) - Browser or mobile app - Telephony (
telephony) - Phone calls
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 · 185 lines · 13 tokens per session scan A eea9fe824ba2
init is a skill published in the GitHub repository xx5921/pipecat-mcp-server (0 stars, last pushed 2mo ago), licensed BSD-2-Clause. It adds 13 tokens to every session and 1,717 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…