cargo-orchestrationMake Cargo actually run something, or show what it would run — execute one connector action, run a multi-step workflow, trigger a batch across a whole segment or model, message an AI agent, build or edit a node graph, draw a workflow, tool or play as a diagram, and query the runtime tables (runs, batches, spans, records) with SQL. Triggers: "run this on all my contacts", "execute the action", "kick off a batch", "build a workflow", "schedule a play", "make it run every morning", "ask the agent", "show me the workflow", "what does this tool do", "visualize this play", "draw the graph", "explain this workflow", "how many runs failed today", "what is the output schema for this action", "add a step that". Skip when: explaining why a run misbehaved — use cargo-diagnostics; downloading result files — use cargo-analytics; committing the workflow as code — use cargo-project.
Install via ClawdBot CLI:
clawdbot install cargo-ai/cargo-orchestrationGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
webhook → https://hooks.example.com/doneCalls external URL not in known-safe list
https://github.com/getcargohq/cargo-skillsAudited May 29, 2026 · audit v1.0
Generated Nov 21, 2026
A sales ops team searches the Cargo action catalog for a company-enrichment connector, runs it on a 15-record sample to observe cost and hit rate, then fans out an `action execute-batch` across the full contact list once approved. Results land back on each record for routing to reps.
A growth marketer builds a reusable multi-step tool (enrich → generate message via AI agent → send) using dedicated actions and expressions, then triggers `batch create --workflow-uuid` across an entire model segment. They draw the graph as ASCII first so the team can approve routing and fallback edges before spending credits.
An ops engineer schedules a saved orchestration tool to run every morning so new records are processed and outputs written to runtime tables. They later query `runs`, `batches`, and `spans` with SQL to confirm volumes and catch failures.
A solutions architect drafts a node graph from connector, native, and agent actions, then renders it with `node diagram --format mermaid` for a technical review and `ascii` for a Slack-ready picture. Only after sign-off do they deploy and run via `run create --workflow-uuid`.
A support team wires an AI agent into a workflow that classifies and replies to inbound tickets, using `message create` to interact conversationally and `node execute` to debug individual steps before committing the full graph. Failure counts are checked daily via SQL over runtime tables.
Customers pay per node execution at roughly 0.01 credits each plus connector provider costs, with credit bundles sold in advance. Step-heavy workflows generate predictable recurring consumption.
Teams subscribe for access to the builder, scheduler, and runtime tables, with tiers gated by workflow count, batch volume, and agent messaging.
Agency or consultancy builds and operates Cargo workflows on behalf of clients, charging setup fees and retainers for ongoing batch runs and monitoring.
💬 Integration Tip
Always run a 10–20 record sample with `action execute-batch` and quote both provider cost and node-execution credits before full enrollment, and use `action list` (free) to find the right action before hand-writing JSON.
Scored Sep 28, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...
AI agent for finance search agent tasks