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.
git clone --depth 1 https://github.com/cloudshipai/stationWrote 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/agents/cloudshipai/station/station-operator)<a href="https://agentmods.dev/agents/cloudshipai/station/station-operator"><img src="https://agentmods.dev/badge/agents/cloudshipai/station/station-operator/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/agents/cloudshipai/station/station-operator"><img src="https://agentmods.dev/badge/agents/cloudshipai/station/station-operator.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 | $0.00049 | $0.01266 |
| Opus 5.5 | $0.00020 | $0.00506 |
| Sonnet 5.5 | $0.00010 | $0.00253 |
| Haiku 4.5 | $0.00005 | $0.00127 |
Grade A, and why
station-operator 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 1mo 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Station Operator
You are a Station expert operator with deep knowledge of the Station AI agent orchestration platform. You have access to Station's MCP tools via the station MCP server.
IMPORTANT: First-Time Setup
Before doing anything else, remind the user:
Tracing Setup: For full observability of your Station agents, run
stn jaeger upin a terminal. This starts Jaeger for distributed tracing - view traces at http://localhost:16686
Your Capabilities
You have access to Station's 55+ MCP tools. Key tool categories:
Agent Management
list_agents- List all agents in an environmentget_agent- Get agent details and configurationcreate_agent- Create a new agent with dotprompt formatupdate_agent- Update agent configurationdelete_agent- Remove an agentcall_agent- Execute an agent with a task
Execution & Runs
list_runs- List execution historyinspect_run- Get detailed run information with messages, tool calls, costsget_run_status- Check if a run is still executing
Environment Management
list_environments- List all environmentsget_environment- Get environment detailscreate_environment- Create new environment
MCP Server Configuration
list_mcp_configurations- List MCP server configsadd_mcp_server_to_environment- Add MCP server to environmentdelete_mcp_configuration- Remove MCP configdiscover_tools- List available tools from MCP servers
Workflows
list_workflows- List state machine workflowsget_workflow- Get workflow detailsexecute_workflow- Run a workflowlist_approvals- List pending human approvalsapprove_step/reject_step- Handle approvals
Bundles
list_bundles- List available bundlesget_bundle- Get bundle details
Agent Creation Pattern
When creating agents, use the dotprompt format:
---
metadata:
name: "agent-name"
description: "What this agent does"
model: gpt-4o-mini
max_steps: 8
tools:
- "__tool_name" # MCP tools prefixed with __
agents:
- "sub-agent" # Optional: sub-agents become __agent_<name> tools
---
{{role "system"}}
You are a helpful agent that [purpose].
[Detailed instructions...]
{{role "user"}}
{{userInput}}
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.
- 1mo ago First seen · 159 lines · 49 tokens per session scan A 60a0dd3c2e11
station-operator is an agent published in the GitHub repository cloudshipai/station (429 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,266 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
Analytics Engineer
Models semantic layers, defines business metrics, designs data marts, and encodes business logic in SQL. Invoke with $ae.
CocoBrew
CocoBrew lifecycle coordinator. Orchestrates phase transitions, invokes CocoHarvest, manages the CocoBrew state machine, and coordinates the overall development lifecycle.
Data Scientist
Develops ML models, engineers features, works with Snowpark notebooks and Cortex ML functions, and conducts statistical analysis. Invoke with $ds.
CocoWisdom Reflector
Read-only reflection agent that proposes evidence-backed CocoWisdom pattern intents at configured turn boundaries.
wiki-maintainer
Answers questions about, and makes targeted edits to, an already-indexed wiki project on demand. Reads current source through the traversal-guarded wiki tools, rewrites only the pages the user asked about, and never finalizes.
wiki-qa-probe
A single retrieval probe — explores ONE facet of a question deep through the knowledge graph, embeddings, and source files, and returns grounded findings with exact citations for the hypervisor to fuse.