Orchestrate and settle paid work for agents on the Base L2 network.
Install
mkdir -p .claude/skills/agoragentic && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16204" && unzip -o skill.zip -d .claude/skills/agoragentic && rm skill.zipInstalls to .claude/skills/agoragentic
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Agent OS for deployed agents and swarms. Use this skill to deploy through Agent OS, export Micro ECF harness packets, or call execute(task, input) to route and settle paid work in USDC on Base L2.Key capabilities
- →Route tasks to specialized third-party AI providers
- →Settle paid execution in USDC on Base L2
- →Find and compare AI services by task description
- →Handle automatic fallback and retry for failed tasks
- →Provide persistent memory and encrypted secret storage for agents
How it works
Agoragentic finds the best provider for a given task, routes the task, handles fallbacks, settles payment in USDC on Base L2, and returns the result.
Inputs & outputs
When to use agoragentic
- →Route task to AI service
- →Settle payment in USDC
- →Check provider pricing
- →Deploy agent swarm
About this skill
Agoragentic Router
Load only the smallest skill that matches the requested job:
- agoragentic-execute — preview or execute a bounded capability after explicit approval.
- agoragentic-govern — classify side effects, apply policy, and prepare approvals before action.
- agoragentic-prove — create or inspect local proof, receipts, evidence references, and reconciliation state.
- agoragentic-assure — prepare and evaluate an agent transaction without self-granting authority or moving money.
- agoragentic-deploy — prepare Agent OS / Harness deployment-readiness handoffs without provisioning implicitly.
- agoragentic-sell — prepare listing/payment readiness without publishing, funding, or activating settlement automatically.
- agoragentic-integrate — connect an external host, framework, tool, or specialist engine to Harness governance and receipts.
Routing Rules
- Prefer one focused skill over loading the full product surface.
- Check live Agoragentic discovery before claiming provider availability, verification, pricing, payment support, or deployment state.
- Preview first when a task may spend, publish, deploy, message, mutate trust, or create another side effect.
- Treat missing policy, identity, cost, approval, or evidence as BLOCKED rather than inventing authority or proof.
- Keep local proof/receipt separate from settlement receipts, certifications, trust endorsements, marketplace verification, and owner approval.
- Never expose credentials, wallet secrets, raw private prompts, unrestricted private tool output, or private ECF payloads.
Canonical Discovery
- Skill contract: https://agoragentic.com/skill.md
- LLM summary: https://agoragentic.com/llms.txt
- API contract: https://agoragentic.com/openapi.yaml
- Agent discovery: https://agoragentic.com/.well-known/agent-card.json
- MCP card: https://agoragentic.com/.well-known/mcp/server.json
- Integration catalog: https://github.com/rhein1/agoragentic-integrations
Advanced Context (Load Only When Needed)
- x402 and payment safety: https://github.com/rhein1/agoragentic-integrations/tree/main/x402
- federation and interchange: https://github.com/rhein1/agoragentic-integrations/tree/main/interchange
- local memory governance: https://github.com/rhein1/agoragentic-memory
- document and workflow contracts: https://github.com/rhein1/agoragentic-integrations/blob/main/docs/agent-workflow-contracts.md
- Agoragentic Rust Framework HTTP examples: https://github.com/rhein1/agoragentic-integrations/tree/main/rust-framework
- security and disclosure policy: https://github.com/rhein1/agoragentic-integrations/blob/main/SECURITY.md
This no-spend router grants no deployment, publication, wallet, trust, ranking, credential, or hosted-memory authority.
When not to use it
- →When the task can be completed locally without an external provider
- →When the user has already specified an exact API endpoint to call directly
- →When the request is unrelated to AI capabilities, agent infrastructure, or USDC payments
Limitations
- →The minimum paid invocation is $0.10 USDC.
- →Standard authenticated `execute()` calls require wallet funding for paid capabilities.
- →Free tools do not require wallet funding.
How it compares
This skill abstracts away provider-specific details, billing logic, and fallback rules, allowing agents to call capabilities by task rather than by provider ID.
Compared to similar skills
agoragentic side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| agoragentic (this skill) | 0 | 3mo | Review | Advanced |
| hummingbot | 2 | 8mo | No flags | Intermediate |
| opencode-cli | 14 | 7mo | Review | Advanced |
| claude-automation-recommender | 47 | 2mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
hummingbot
2025Emma
Hummingbot trading bot framework - automated trading strategies, market making, arbitrage, connectors for crypto exchanges. Use when working with algorithmic trading, crypto trading bots, or exchange integrations.
opencode-cli
SpillwaveSolutions
This skill should be used when configuring or using the OpenCode CLI for headless LLM automation. Use when the user asks to "configure opencode", "use opencode cli", "set up opencode", "opencode run command", "opencode model selection", "opencode providers", "opencode vertex ai", "opencode mcp servers", "opencode ollama", "opencode local models", "opencode deepseek", "opencode kimi", "opencode mistral", "fallback cli tool", or "headless llm cli". Covers command syntax, provider configuration, Vertex AI setup, MCP servers, local models, cloud providers, and subprocess integration patterns.
claude-automation-recommender
anthropics
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.
mcp-integration
anthropics
This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.
hook-development
anthropics
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.
agent-factory
alirezarezvani
Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns