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/quickchatai/quickchat-claude-plugin/launch-agentnpx skills add quickchatai/quickchat-claude-plugin --skill launch-agentgit clone --depth 1 https://github.com/quickchatai/quickchat-claude-pluginWhat 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 | $0.00109 | $0.00963 |
| Opus 5 | $0.00055 | $0.00481 |
| Sonnet 5 | $0.00022 | $0.00193 |
| Haiku 4.5 | $0.00011 | $0.00096 |
Grade A, and why
launch-agent 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 2d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Launch a new Agent
Stand up a working Agent in one guided flow. Most people running this have just connected Quickchat and have an empty Agent, so build something before you report anything.
Before you start
- Ask whether they have a website to build from. That answer picks the path below.
- Explain this creates a real Agent on the FREE tier (no charge, no card).
Path A — they have a website
- Call
create_assistantwith confirm=true (andnameif given). Creation is guarded by confirm=true and capped at 5/hour. Tell the user the newscenario_id. - Call
onboard_assistant_from_urlwith that scenario_id and the URL. Say out loud that this takes 20-60 seconds while it scrapes the site, writes the persona and embeds the content — silence here is where people give up. It OVERWRITES configuration, so run it only on the freshly created Agent, never an established one. - Poll
get_assistant_settingsuntilonboarding_from_url_completedis true. If it reportsonboarding_progress_trackedfalse there is no completion signal — read the settings once after ~60s instead. - Show what was generated: the name, the main prompt, the guidelines and the language it picked.
If the URL is rejected as a placeholder or marketplace domain, ask for their own business website rather than retrying the same URL.
Path B — no website
Do NOT create an empty Agent and stop. Interview first, in one short round of questions:
- What does the business do, and what is it called?
- Who will be talking to the Agent (customers, members, players, staff)?
- What tone should it take?
- What are the top 3 questions it must answer?
Then create a configured Agent in a single call — create_assistant accepts the
settings inline:
nameandone_word_description— what the Agent is calledshort_description— the main prompt: role, what it helps with, what it must not guess atai_commands— one short rule per item, from their must-answer questionsgreeting— the first line a visitor seeslanguage_chosen— the language they answered in
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.
- 2d ago First seen · 91 lines · 109 tokens per session scan A 296b99d05bee
launch-agent is a skill published in the GitHub repository quickchatai/quickchat-claude-plugin (1 stars, last pushed 8d ago), licensed MIT. It adds 109 tokens to every session and 963 once invoked, about $0.0005 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
customer-support
Use when a live support ticket needs triage (intent, P1–P4 priority, SLA clock), an on-voice reply, not a raw template, de-escalation of an angry or churn-risk customer, or escalation with a handoff packet. NOT the help-center article it links to (that is technical-writing), a win-back program (retention), or the…
helpscout-navigator
Use when searching HelpScout tickets, customers, or organizations. Provides correct tool selection, required sequencing, and prevents common mistakes. Triggers on "search helpscout", "find tickets", "check support inbox", "helpscout conversations", "look up customer", "find organization", "customer history".
deskcrew-support
Run a customer support desk on DeskCrew. Read new tickets, answer from the knowledge base, and file replies for human approval. Use when handling customer support. Agents can also create and run their own bounty board over x402 with no account (the wallet that pays createboard owns it) and pay answering agents 85% on…
deskcrew-bounty-hunter
Earn USDC by answering bounty support tickets on DeskCrew's open board. Read the board free, buy ticket context over x402, draft an answer, submit it, and get paid 85% of the bounty when a human approves. Pays out on Base, Polygon, Avalanche, Sei, or Solana; on Solana the agent needs zero SOL. Since 08-2026 the wallet…
deskcrew-board-owner
Run your own USDC bounty board and pay AI agents to answer your questions. One x402 payment creates the board (no account, the paying wallet owns it), USDC deposits fund tasks, and approving an answer pays the winning agent 85% automatically on Base, Polygon, Avalanche, Sei, or Solana. Use when asked to delegate work…
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).