ccc-connect

ccc-connect is a skill for Claude Code, Codex from KevinZai/commander. It costs 50 tokens per session (4,557 once invoked), scanned B, original, MIT.

A connector setup wizard for linking Claude Code to external services such as Notion, Slack, GitHub, databases, and design tools through MCP connectors. MCP is a way for the agent to access connected services.

In plain words
What is it for?
Connecting the tools an agent needs for tasks such as issue tracking, backend work, design work, and team communication.
Why use it?
It guides you through choosing and connecting services instead of requiring manual configuration, while keeping installation opt-in.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/kevinzai/commander/ccc-connect
Any agent
npx skills add KevinZai/commander --skill ccc-connect
Clone the repo
git clone --depth 1 https://github.com/KevinZai/commander

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ccc-connect

README.md
[![agentmods](https://agentmods.dev/badge/skills/kevinzai/commander/ccc-connect.svg)](https://agentmods.dev/skills/kevinzai/commander/ccc-connect)
Your own site
<a href="https://agentmods.dev/skills/kevinzai/commander/ccc-connect"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-connect.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,557 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00050 $0.04557
Opus 5 $0.00025 $0.02278
Sonnet 5 $0.00010 $0.00911
Haiku 4.5 $0.00005 $0.00456

Measured 4d ago against content hash 55ee1c754e0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

ccc-connect scanned grade B 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 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 600 ~/.claude/commander/connections/<name>.json && \
commander/cowork-plugin-codex/skills/ccc-connect/SKILL.md · 357 lines

How it starts

The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.

$ccc-connect — MCP Connector Wizard

Click-to-connect opt-in MCP servers. Never auto-installs — always user-initiated.

Affiliate disclosure (ALWAYS show at top of every $ccc-connect response)

💸 Some links below are affiliate — CCC may earn a commission at no cost to you.
[Disclosure](https://docs.commanderplugin.com/affiliate-disclosure)

Response shape (EVERY time)

1. Brand header

**CC Commander** · Connector Wizard · [Docs](https://commanderplugin.com)

2. Context strip

Detect currently-connected MCPs in parallel via a single Bash call:

  • claude mcp list 2>/dev/null | grep -c '^ ' || echo 0 → count
  • claude mcp list 2>/dev/null | awk '{print $1}' | tr '\n' ',' || echo "none" → names

Render:

🔌 Currently connected: MCPs · <comma-list or 'none yet'>

If none connected: "🔌 No MCPs wired up — pick a category below and I'll walk you through."

3. Category picker — AskUserQuestion

question: "Which category?"
header: "Connect"
multiSelect: false
options:
  - label: "📋 Tasks"
    description: "Linear — first-class CC Commander integration."
    preview: "Best for: issue tracking, sprint planning, CC-* task routing."
  - label: "🗄️ Backend"
    description: "Supabase (first-class), Neon, Postgres — databases for shipped apps."
    preview: "Best for: SaaS backends, auth, schema inspection. ⭐ Supabase default."
  - label: "🚀 Hosting"
    description: "Vercel, Fly.io, Cloudflare — deploy and edge."
    preview: "Best for: web deploys, Docker services, Workers + R2."
  - label: "⚡ Cache / Queue"
    description: "Upstash — Redis + Kafka serverless."
    preview: "Best for: rate limiting, job queues, session storage."
  - label: "📚 Knowledge"
    description: "Notion — pages, databases, comments."
    preview: "Best for: docs, wikis, team knowledge bases."
  - label: "💬 Comms"
    description: "Slack, Discord — team and community channels."
    preview: "Best for: team workflows, Pro community, notifications."
  - label: "🚨 Observability"
    description: "Sentry — errors, performance, releases."
    preview: "Best for: monitoring shipped apps, alerting on regressions."
  - label: "💳 Billing"
    description: "Stripe — payments for SaaS."
    preview: "Best for: subscription management, payment links, invoices."
  - label: "🤖 Automation"
    description: "Browserbase, Playwright, Zapier, n8n — browser + workflows."
    preview: "Best for: remote headless browsers, cross-app automation."
  - label: "🧬 Agent harness"
    description: "acpx — bring-your-own agent harness for headless agent-to-agent runs."
    preview: "Best for: parallel/background CC sessions, crash-resilient agent dispatch."
  - label: "✉️ Email"
    description: "Resend, AgentMail — transactional and agent-native email."
    preview: "Best for: SaaS emails, agent inbox workflows."
  - label: "🔬 Research"
    description: "Tavily, Firecrawl, Exa, Context7 — web search + scraping."
    preview: "Best for: deep research, competitive analysis, live docs."
  - label: "🎨 Design & Automation"
    description: "Figma, Zapier, n8n — design sync + cross-app workflows."
    preview: "Best for: design handoff, automated triggers."

Read the full file on GitHub · 357 lines

Changes

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.

  1. 4d ago First seen · 357 lines · 50 tokens per session scan B 55ee1c754e0b

Subscribe to this mod's changes

ccc-connect is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 4,557 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

postgres-database-migration

Use this skill for planning, testing, and safely executing PostgreSQL schema migrations — especially when working with production data or shared databases. Trigger when user asks to: Test a schema migration before applying it to production Add, remove, or rename columns safely on a live table Change a column's data…

timescale/pg-aiguide · 222 tokens

setup-timescaledb-hypertables

Use this skill when creating database schemas or tables for Timescale, TimescaleDB, TigerData, or Tiger Cloud, especially for time-series, IoT, metrics, events, or log data. Use this to improve the performance of any insert-heavy table. Trigger when user asks to: Create or design SQL schemas/tables AND…

timescale/pg-aiguide · 219 tokens

migrate-postgres-tables-to-hypertables

Use this skill to migrate identified PostgreSQL tables to Timescale/TimescaleDB hypertables with optimal configuration and validation. Trigger when user asks to: Migrate or convert PostgreSQL tables to hypertables Execute hypertable migration with minimal downtime Plan blue-green migration for large tables Validate…

timescale/pg-aiguide · 181 tokens

pgvector-semantic-search

Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…

timescale/pg-aiguide · 190 tokens

find-hypertable-candidates

Use this skill to analyze an existing PostgreSQL database and identify which tables should be converted to Timescale/TimescaleDB hypertables. Trigger when user asks to: Analyze database tables for hypertable conversion potential Identify time-series or event tables in an existing schema Evaluate if a table would…

timescale/pg-aiguide · 184 tokens

postgres-hybrid-text-search

Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). Trigger when user asks to: Combine keyword and semantic search Implement hybrid search or multi-modal retrieval Use BM25/pgtextsearch with pgvector together Implement RRF (Reciprocal…

timescale/pg-aiguide · 162 tokens