compozy-agent-config

A set of examples for configuring Compozy agents, including their instructions, tools, actions, models, and connections to external services.

In plain words
What is it for?
Use it when defining an agent’s provider, model, instructions, tools, actions, structured output, or external integrations.
Why use it?
It gives developers concrete configuration patterns instead of requiring them to design the format from scratch.

Cursor rule for Cursor

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 rules/compozy/gograph/compozy-agent-config
Clone the repo
git clone --depth 1 https://github.com/compozy/gograph

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 575 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.00575
Opus 5 $0.00000 $0.00287
Sonnet 5 $0.00000 $0.00115
Haiku 4.5 $0.00000 $0.00057

Measured 2d ago against content hash 5be9f56913c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compozy-agent-config 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 2d 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.

.cursor/rules/compozy-agent-config.mdc · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compozy Agent Configuration Examples

<configuration_overview type="agent_config"> Agent configuration defines AI agents with instructions, tools, actions, and MCP integrations for workflow execution. </configuration_overview>

Basic Agent Configuration

<agent_config_pattern type="basic_agent">

resource: agent
id: tourist_guide
description: A helpful tourist guide assistant
version: 0.1.0

config:
  provider: groq
  model: llama-3.3-70b-versatile
  api_key: "{{ .env.GROQ_API_KEY }}"

instructions: |
  You are a helpful tourist guide assistant specialized in {{ .workflow.input.city }}
  Your capabilities:
  - Provide thoughtful recommendations for activities
  - Suggest appropriate clothing based on weather
  Always respond in valid JSON format when json_mode is enabled.

tools:
  - $ref: local::tools.#(id=="weather_tool")

actions:
  - id: get_weather
    prompt: |
      What is the current weather in {{ .workflow.input.city }}?

  - id: suggest_activities
    json_mode: true
    prompt: |
      Given the current conditions: {{ .tasks.weather.output | toJson }}
      Suggest appropriate activities for these weather conditions
    output:
      type: object
      properties:
        activities:
          type: array
          items:
            type: string
      required:
        - activities

</agent_config_pattern>

Agent with MCP Integration

<agent_config_pattern type="agent_with_mcp">

resource: agent
id: file_reader
description: An agent that uses MCP tools to read and list files
version: 0.1.0

config:
  provider: groq
  model: llama-3.3-70b-versatile
  api_key: "{{ .env.GROQ_API_KEY }}"

instructions: |
  You are a file management assistant that uses MCP tools.
  Use MCP tools to check what files exist and read contents when needed.

mcps:
  - id: file_server
    transport: stdio
    command: npx
    args:
      - -y
      - "@modelcontextprotocol/server-filesystem"
      - "./"
    proto: "2025-03-26"
    start_timeout: 15s

actions:
  - id: list_saved_files
    prompt: |
      Use MCP tools to list files in the current directory.
      Look for results.json and results.txt files.
      Use the read_directory MCP tool to list contents.

</agent_config_pattern>

Read the full file on GitHub · 97 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. 2d ago First seen · 97 lines · 0 tokens per session scan A 5be9f56913c6

Subscribe to this mod's changes

compozy-agent-config is a cursor rule published in the GitHub repository compozy/gograph (9 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 575 tokens. 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 2026-08-31.