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 quickchatai/quickchat-claude-plugin --skill setupgit clone --depth 1 https://github.com/quickchatai/quickchat-claude-pluginWrote 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/quickchatai/quickchat-claude-plugin/setup)<a href="https://agentmods.dev/skills/quickchatai/quickchat-claude-plugin/setup"><img src="https://agentmods.dev/badge/skills/quickchatai/quickchat-claude-plugin/setup/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/quickchatai/quickchat-claude-plugin/setup"><img src="https://agentmods.dev/badge/skills/quickchatai/quickchat-claude-plugin/setup.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 | $0.00079 | $0.00589 |
| Opus 5.5 | $0.00032 | $0.00236 |
| Sonnet 5.5 | $0.00016 | $0.00118 |
| Haiku 4.5 | $0.00008 | $0.00059 |
Grade A, and why
setup 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 10d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connect Quickchat AI
The plugin ships a remote MCP server at https://app.quickchat.ai/v1/api/mcp/rpc.
It authenticates with OAuth, so there is no API key to paste.
Connect
- Claude on the web or desktop, and Cowork: open Customize > Plugins, select Quickchat AI and open its Connectors tab. If the connector shows Not added, add it, then connect it. The same connector is listed in the Claude Directory as Quickchat AI, where the button reads Connect to Claude.
- Claude Code: run
/mcp, choose the Quickchat server and sign in.
Either way a Quickchat sign-in page opens in the browser. Sign in with a Quickchat account, or create one: signing up here also creates a free AI Agent. Approve, and the browser returns to Claude.
Confirm it worked
Call whoami, then list_scenarios. A successful list_scenarios returns the
AI Agents the account can reach, with the user's role on each.
- An entry with
configured: falseis the empty Agent the account came with. Offer thelaunch-agentskill to set it up from a website or a short interview. - An empty list means the account can't reach any Agent yet. Ask the user to get a role from an admin of their Quickchat organization.
- An authentication error means the OAuth flow didn't complete. Ask the user to reconnect rather than retrying the tool.
What the account controls
Every tool enforces the same per-Agent roles as the Quickchat dashboard, so the connection reaches only the Agents and conversations that account can already reach. Some write operations need Editor or Support; a few also depend on the plan's limits.
Where to go next
| The user wants to | Skill |
|---|---|
| Build a new Agent from a website or an interview | launch-agent |
| Put an Agent live on a website, chat page, Discord, Telegram, Instagram, Slack or email | deploy-agent |
| See how an Agent is performing | performance-review |
| Find conversations that need a human | conversation-triage |
| Audit and improve settings or knowledge | improve-agent |
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.
- 10d ago Changed · +4 lines 6a6d09f51137
- 1mo ago First seen · 55 lines · 79 tokens per session scan A 64c906e686ec
setup is a skill published in the GitHub repository quickchatai/quickchat-claude-plugin (1 stars, last pushed 2d ago), licensed MIT. It adds 79 tokens to every session and 589 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
review
5-pass structured code review — correctness, security, performance, readability, consistency.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.
pr-review
Comprehensive PR review across six dimensions — cost impact, environment drift, ownership gaps, SOC 2 compliance, deprecated API / version hygiene, and rollback feasibility. Each mode inspects the diff and current file state, reports findings with severity, and recommends concrete fixes. Use when preparing a PR for…
extract-resume
Parse a resume's uploaded PDF into structured JSON (basics, experience, projects, skills, education) and save it to the editor.
ensure-pipelines-host
Ensures the tenant has a usable Power Platform Pipelines host environment before any pipeline operation runs. Detects host state via the same resolution order as the Power Apps UI (org-db setting → BAP env metadata → default-custom-host setting); if any existing host (Platform or Custom) is found, uses it. If no host…
delegate
Let Claude Architect route a versioned implementation spec through the trusted MCP runtime, independently review the Candidate Artifact, record a decision, and integrate only accepted bytes. Use for implementation delegation, Producer selection, or commitment-boundary review.