cursor_dev_workflow

A set of Cursor editor rules for using Conductor Tasks with Cursor’s code generation and chat features. It tells the developer to keep the task’s ID and details in context and review generated changes.

In plain words
What is it for?
Implementing or changing code from Conductor tasks, asking Cursor for clarification or debugging help, and reviewing the generated work.
Why use it?
AI-generated code can lose track of the task it is meant to solve. These rules keep Cursor’s suggestions tied to a named Conductor task and encourage checking the result.

Cursor rule

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/hridaya423/conductor-tasks/cursor_dev_workflow
Clone the repo
git clone --depth 1 https://github.com/hridaya423/conductor-tasks
Per session 871 This file is loaded in full into every session.
When invoked 871 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 $0.00871 $0.00871
Opus 5 $0.00436 $0.00436
Sonnet 5 $0.00174 $0.00174
Haiku 4.5 $0.00087 $0.00087

Measured 2d ago against content hash 04eaa1c02e96, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursor_dev_workflow 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.

src/ide/rule_templates/cursor_dev_workflow.mdc · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.


description: Cursor-specific development workflow enhancements when using Conductor Tasks globs: */ alwaysApply: true

Cursor Development Workflow with Conductor Tasks

This document outlines how to best utilize Cursor's unique capabilities alongside the Conductor Tasks AI Development Workflow.

Leveraging Cursor's AI Features for Task Implementation

  1. Code Generation & Modification:

    • When a Conductor task requires writing or modifying code, utilize Cursor's built-in AI code generation (e.g., "Generate code for...", "Edit selection...") for relevant segments.
    • Always provide the Conductor task ID and its details as context to Cursor's AI for more relevant suggestions. For example: "Implement the following for Conductor Task TSK-42 (details: ): ".
    • After Cursor generates code, critically review it against the task requirements.
  2. Chat for Clarification & Debugging:

    • Use Cursor's chat feature to discuss complex parts of a task, debug issues, or explore alternative implementations.
    • Frame your questions to the chat in the context of the Conductor task you are working on.
    • Summarize key insights or decisions from Cursor chat discussions into the Conductor task notes using `add-task-note --id <task_id> --note "Insights from Cursor chat: ..." `.
  3. Diffing and Review:

    • Use Cursor's diff views to review changes you've made (or Cursor's AI has made) before marking a task segment as complete or adding notes.
    • Ensure changes align with the Conductor task objectives.

Integrating Conductor Tasks into Cursor's Flow

  1. Starting Your Session:
    • Use `get-next-task` (via MCP tool) to identify your current Conductor task.
    • Keep the task details (obtained via `get-task`) readily available, perhaps copied into a comment in your current file or a scratchpad in Cursor, for easy reference while coding.
    • The user might use `visualize-tasks-kanban` in their terminal; you rely on `list-tasks` and `get-task` for your information.

Read the full file on GitHub · 58 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 · 58 lines · 871 tokens per session scan A 04eaa1c02e96

Subscribe to this mod's changes

cursor_dev_workflow is a cursor rule published in the GitHub repository hridaya423/conductor-tasks (74 stars, last pushed 7mo ago), licensed MIT. It adds 871 tokens to every session, about $0.0044 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.