compozy-task-patterns

A reference for choosing task structures and execution strategies in Compozy workflows, such as basic, grouped, parallel, conditional, signal-based, and aggregate tasks.

In plain words
What is it for?
Use it when writing Compozy workflow configurations with tool calls, sub-tasks, parallel work, routing, or combined results.
Why use it?
It helps turn a workflow into the right set of steps and define what happens when tasks succeed or fail.

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-task-patterns
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 1,443 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 $0.01443
Opus 5 $0.00000 $0.00722
Sonnet 5 $0.00000 $0.00289
Haiku 4.5 $0.00000 $0.00144

Measured yesterday against content hash 00df5e7366af, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compozy-task-patterns 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 yesterday.

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-task-patterns.mdc · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compozy Task Patterns

<configuration_overview type="task_patterns"> Task patterns define different types of task execution strategies including basic, composite, parallel, collection, router, signal, and aggregate tasks. </configuration_overview>

Basic Task Pattern

<task_patterns type="basic_task">

# Basic task with tool execution
- id: weather
  type: basic
  $use: tool(local::tools.#(id=="weather_tool"))
  with:
    city: "{{ .workflow.input.city }}"
  outputs:
    temperature: "{{ .output.temperature }}"
    city: "{{ .workflow.input.city }}"
  on_success:
    next: next_task

</task_patterns>

Composite Task Pattern

<task_patterns type="composite_task">

# Composite task containing multiple sub-tasks
- id: root_composite
  type: composite
  strategy: fail_fast
  tasks:
    - id: subtask_1
      type: basic
      $use: tool(local::tools.#(id=="echo_tool"))
      with:
        message: "First subtask"
    - id: subtask_2
      type: basic
      $use: tool(local::tools.#(id=="echo_tool"))
      with:
        message: "Second subtask"

</task_patterns>

Parallel Task Pattern

<task_patterns type="parallel_task">

# Parallel task execution
- id: parallel_section
  type: parallel
  strategy: wait_all  # or race
  tasks:
    - id: task_a
      type: basic
      $use: tool(local::tools.#(id=="echo_tool"))
      with:
        message: "Parallel Task A"
    - id: task_b
      type: basic
      $use: tool(local::tools.#(id=="echo_tool"))
      with:
        message: "Parallel Task B"

</task_patterns>

Collection Task Pattern

<task_patterns type="collection_task">

# Collection task for processing arrays
- id: collection_section
  type: collection
  mode: parallel  # or sequential
  strategy: best_effort  # or fail_fast
  items: "{{ .workflow.input.test_data }}"
  task:
    id: "process-{{ .index }}"
    type: basic
    $use: tool(local::tools.#(id=="echo_tool"))
    with:
      message: "Processing item: {{ .item }} at index {{ .index }}"

</task_patterns>

Read the full file on GitHub · 267 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. yesterday First seen · 267 lines · 0 tokens per session scan A 00df5e7366af

Subscribe to this mod's changes

compozy-task-patterns 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 1,443 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.