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/hridaya423/conductor-tasksWrote 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/rules/hridaya423/conductor-tasks/cursor_dev_workflow)<a href="https://agentmods.dev/rules/hridaya423/conductor-tasks/cursor_dev_workflow"><img src="https://agentmods.dev/badge/rules/hridaya423/conductor-tasks/cursor_dev_workflow/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/rules/hridaya423/conductor-tasks/cursor_dev_workflow"><img src="https://agentmods.dev/badge/rules/hridaya423/conductor-tasks/cursor_dev_workflow.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 | $0.00871 | $0.00871 |
| Opus 5.5 | $0.00348 | $0.00348 |
| Sonnet 5.5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
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 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 — 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
-
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.
-
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: ..." `.
-
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
- 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.
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 · 58 lines · 871 tokens per session scan A 04eaa1c02e96
cursor_dev_workflow is a cursor rule published in the GitHub repository hridaya423/conductor-tasks (74 stars, last pushed 8mo ago), licensed MIT. It adds 871 tokens to every session, about $0.0035 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 cursor rules, from other repositories
php-transport-implementation
Guidelines for implementing transport layers in PHP MCP SDK.
php-types-validation
Guidelines for type definitions and validation in PHP MCP SDK.
php-client-implementation
Guidelines for implementing MCP clients in PHP.
php-server-implementation
Guidelines for implementing MCP servers in PHP.
php-mcp-sdk-main
This is the PHP implementation of the Model Context Protocol (MCP) SDK, following the patterns established by the TypeScript SDK.
guide-for-using-mcp-servers
Helps organize thoughts, break down problems, and build reasoning step by step.