workflow

Workflow rules for Git, Taskmaster, Memory MCP, and Context7 MCP, which are tools for version control, task planning, stored project knowledge, and current library documentation.

In plain words
What is it for?
Use them during development, library-specific implementation, documentation lookup, task planning, and knowledge-graph updates.
Why use it?
They define when each tool should be used and require confirmation before changing stored knowledge, reducing accidental project changes and outdated implementation guidance.

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/jpke/cursor-vibe-coding-template/workflow
Clone the repo
git clone --depth 1 https://github.com/jpke/cursor-vibe-coding-template

Made for: Cursor.

Per session 1,178 This file is loaded in full into every session.
When invoked 1,178 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 $0.01178 $0.01178
Opus 5 $0.00589 $0.00589
Sonnet 5 $0.00236 $0.00236
Haiku 4.5 $0.00118 $0.00118

Measured yesterday against content hash 2f16d6dc6d27, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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/workflow.mdc · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Template Setup Workflow

For detailed steps on template setup when initializing a project, see template_setup.mdc.

IMPORTANT: Template initialization is ONLY about setting up project structure and configuration. TaskMaster, PRD creation, and git setup are separate workflows that require explicit user requests.

MCP Server Workflows

Memory MCP

  • User Confirmation Required: Before creating, updating, or deleting any entities or relationships in the Memory MCP's knowledge graph, I must first explain what I intend to do and ask for your explicit confirmation.

Context7 MCP

  • Purpose: Use Context7 MCP to fetch current, accurate library documentation and implementation examples during development tasks.
  • When to Use: Before implementing features with specific libraries, when encountering library-specific errors, for version-specific guidance, when user asks about library features, during code reviews, for implementation examples
  • Required Two-Step Process:
    1. First: Use mcp_context7_resolve-library-id to convert library name (e.g., "react", "nextjs") to Context7-compatible ID
    2. Then: Use mcp_context7_get-library-docs with the resolved ID to fetch documentation
  • Best Practices:
    • Always resolve library ID first - never skip this step
    • Use topic parameter to focus on specific areas (e.g., "hooks", "routing", "authentication")
    • Adjust tokens parameter based on complexity (default 10000, increase for comprehensive docs)
    • Combine with research tool when Context7 doesn't have the specific library

Taskmaster Workflow

  • PRD as GitHub Issue:
    1. After generating a Product Requirements Document (PRD), I will work with you to validate its contents.
    2. Once you accept the PRD, I will create a GitHub Issue in the project's repository containing the full text of the PRD.
    3. This GitHub Issue will serve as the single source of truth for the project's requirements.
    4. DELETE the local PRD file (.taskmaster/docs/*.md) immediately after creating the GitHub Issue to prevent confusion and ensure the GitHub Issue remains the authoritative version.
  • Task Generation Trigger: I will only generate tasks from the PRD Issue after you explicitly tell me to "start working on the PRD" or give a similar instruction.
  • Task Confirmation: After Taskmaster generates tasks, I must confirm with you which task to begin work on before executing any of them.

Read the full file on GitHub · 82 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 · 82 lines · 1,178 tokens per session scan A 2f16d6dc6d27

Subscribe to this mod's changes

workflow is a cursor rule published in the GitHub repository jpke/cursor-vibe-coding-template (16 stars, last pushed 1y ago), licensed MIT. It adds 1,178 tokens to every session, about $0.0059 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.