By contro-com
Contro Agentic Card skill for setup from scratch, MCP host configuration, Budget policy context, Mandate state handling, and no-card-data payment safety.
Contro skills for AI coding assistants. Provides guided Contro Agentic Card setup, MCP connection help, Budget and Mandate guidance, payment approval handling, reveal safety, 3DS guidance, and denial troubleshooting.
| Skill | Description |
|---|---|
contro-agentic-card | Set up Contro Agentic Card from scratch, connect an AI agent through Contro MCP, and safely handle Budget-backed payment Mandates. |
Security warning: never expose Contro Agent bearer tokens, reveal URLs, card details, OTPs, provider credentials, or checkout cookies in chat messages, logs, screenshots, or git commits. Pairing instructions are chat-safe because they contain only a short-lived Pairing code.
npx skills add contro-com/contro-skills
Works with skill-compatible assistants that can install from GitHub repositories.
Tell Codex:
Fetch and follow instructions from https://raw.githubusercontent.com/contro-com/contro-skills/refs/heads/main/.codex/INSTALL.md
Then start a new thread and ask:
Use $contro-agentic-card to help me set up Contro Agentic Card from scratch.
Tell Codex:
Fetch and follow instructions from https://raw.githubusercontent.com/contro-com/contro-skills/refs/heads/main/.codex/INSTALL.md
If Skills are enabled for your Claude account, download this repository and import skills/contro-agentic-card as a Claude Skill. If Claude asks for an upload, zip that folder first.
After import, ask Claude:
Use the Contro Agentic Card skill to help me connect my agent to Contro.
Run in Claude Code:
/plugin marketplace add contro-com/contro-skills
/plugin install contro-skills
Tell OpenClaw:
Fetch and follow instructions from https://raw.githubusercontent.com/contro-com/contro-skills/refs/heads/main/.openclaw/INSTALL.md
Tell Hermes Agent:
Fetch and follow instructions from https://raw.githubusercontent.com/contro-com/contro-skills/refs/heads/main/.hermes-agent/INSTALL.md
Install with the recommended command above, or use Cursor's skill/plugin install flow for:
https://github.com/contro-com/contro-skills.git
Setup from scratch:
contro-agentic-card -> Contro sign-in -> passkey or 2FA -> Wallet KYC/card readiness -> Agent setup -> Budget setup -> MCP connection
Connect an agent:
contro-agentic-card -> create Agent -> assign Budget -> copy Pairing instruction -> redeem Pairing code -> add returned Contro MCP config to agent host -> verify list_budgets
Payment request:
contro-agentic-card -> gather merchant/amount/currency/cart -> list_budgets -> request_payment -> wait for approval or release -> checkout -> get_payment
Troubleshooting:
contro-agentic-card -> inspect safe reason -> fix Contro blocker -> retry only when the same purchase intent is still valid
Contro Agentic Card uses a Contro MCP server configured through Pairing. Contro Mobile or web shows a one-line Pairing instruction such as Connect Contro with pairing code: AB2C-45AD in production, or Connect Contro using this {pairingUrl}/{pairingCode} outside production.
The agent redeems the Pairing code and receives host-oriented MCP configuration. Do not paste real Agent bearer tokens into public examples. Use placeholders in docs:
{
"mcpServers": {
"contro": {
"url": "{MCP_URL_RETURNED_BY_PAIRING_REDEMPTION}",
"headers": {
"Authorization": "Bearer {AGENT_BEARER_TOKEN_RETURNED_TO_HOST_CONFIG}"
}
}
}
}
Contro Agentic Card lets an AI agent request bounded payment authority. It does not give the agent the user's primary card.
A released Mandate means Contro released bounded credential authority for checkout. It does not mean the merchant payment has completed.
Agents must not work around Contro approval, Budget limits, merchant controls, 3DS, provider declines, or card-network rules.
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub contro-com/contro-skills --plugin contro-skillsIntelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Give your AI a memory — mine projects and conversations into a searchable palace. 33 MCP tools, auto-save hooks, and guided setup.
MCP server that saves 98% of your context window with session continuity. Sandboxed code execution in 11 languages, FTS5 knowledge base with BM25 ranking, and automatic state restore across compactions.
Advanced frontend design plugin with interactive wizard, trend research, moodboard creation, color/typography selection, and browser-based inspiration analysis
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.