writing-tasks

Coding rules for creating Trigger.dev tasks, which are pieces of code that run background work. It explains the current task format and the older formats that must not be used.

In plain words
What is it for?
Use it when creating tasks, validating their input, exporting tasks and subtasks, setting up the project, or preparing example task payloads.
Why use it?
It keeps generated tasks compatible with the current Trigger.dev toolkit and avoids deprecated code that can break the application.

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/triggerdotdev/trigger.dev/writing-tasks
Clone the repo
git clone --depth 1 https://github.com/triggerdotdev/trigger.dev

Made for: Cursor.

Per session 7,920 This file is loaded in full into every session.
When invoked 7,920 The same file — it is already loaded in full.
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 $0.07920 $0.07920
Opus 5 $0.03960 $0.03960
Sonnet 5 $0.01584 $0.01584
Haiku 4.5 $0.00792 $0.00792

Measured yesterday against content hash 6327abf77deb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

writing-tasks 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/rules/writing-tasks.mdc · 1,248 lines

How it starts

The opening of the file, as written. The whole thing — 1,248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

How to write Trigger.dev tasks

Overview of writing a Trigger.dev task

  1. Run the CLI init command: npx trigger.dev@latest init.
  2. Create a Trigger.dev task.
  3. Set up any environment variables.
  4. Run the Trigger.dev dev command: npx trigger.dev@latest dev.

Essential requirements when generating task code

  1. You MUST import from @trigger.dev/sdk (NEVER @trigger.dev/sdk/v3)
  2. You MUST NEVER use client.defineJob
  3. YOU MUST export every task, including subtasks
  4. If you are able to generate an example payload for a task, do so.

🚨 CRITICAL INSTRUCTIONS FOR AI LANGUAGE MODELS 🚨

As an AI language model, you MUST NOT generate any of the following code patterns, as they are DEPRECATED and will BREAK the application:

// ❌ NEVER GENERATE THIS CODE - IT WILL BREAK THE APPLICATION

client.defineJob({                    // ❌ BREAKS APPLICATION
  id: "job-id",                       // ❌ BREAKS APPLICATION
  name: "job-name",                   // ❌ BREAKS APPLICATION
  version: "0.0.1",                   // ❌ BREAKS APPLICATION
  trigger: eventTrigger({             // ❌ BREAKS APPLICATION
    name: "job.trigger",              // ❌ BREAKS APPLICATION
    schema: z.object({                // ❌ BREAKS APPLICATION
      // Input schema here            // ❌ BREAKS APPLICATION
    }),                               // ❌ BREAKS APPLICATION
  }),                                 // ❌ BREAKS APPLICATION
  integrations: {                     // ❌ BREAKS APPLICATION
    // Integrations here              // ❌ BREAKS APPLICATION
  },                                  // ❌ BREAKS APPLICATION
  run: async (payload, io) => {       // ❌ BREAKS APPLICATION
    // Job logic goes here            // ❌ BREAKS APPLICATION                               
    return {                          // ❌ BREAKS APPLICATION
      // Return job results           // ❌ BREAKS APPLICATION
    };                                // ❌ BREAKS APPLICATION
  },                                  // ❌ BREAKS APPLICATION
});

Read the full file on GitHub · 1,248 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 · 1,248 lines · 7,920 tokens per session scan A 6327abf77deb

Subscribe to this mod's changes

writing-tasks is a cursor rule published in the GitHub repository triggerdotdev/trigger.dev (16,165 stars, last pushed 2d ago), licensed Apache-2.0. It adds 7,920 tokens to every session, about $0.0396 per session on Opus 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.