task-execution

A task workflow rule for Unreal Engine development that requires test-driven development, modular implementation, and GitHub task tracking.

In plain words
What is it for?
It guides branch creation, moving GitHub tasks to In Progress, writing failing tests first, implementing the smallest passing change, and refactoring safely.
Why use it?
It creates a repeatable process for starting work, testing it, integrating it with project tracking, and keeping changes maintainable.

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/stramp/lost-mines-phandelver/task-execution
Clone the repo
git clone --depth 1 https://github.com/Stramp/Lost-Mines-Phandelver

Made for: Cursor.

Per session 1,894 This file is loaded in full into every session.
When invoked 1,894 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 $0.01894 $0.01894
Opus 5 $0.00947 $0.00947
Sonnet 5 $0.00379 $0.00379
Haiku 4.5 $0.00189 $0.00189

Measured yesterday against content hash 7179f834f55d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-execution 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/task-execution.mdc · 275 lines

How it starts

The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🎯 Task Execution Rules

🚨 MAIN RULE - INTEGRITY AND MODULARITY 🚨

ALWAYS follow these rules when executing any task:

  • TDD mandatory: All tasks must be tested and all tests must pass
  • Modularity: Focus only on task integrity while always being modular
  • GitHub Integration: Move task from TODO to In Progress on GitHub
  • Branch Creation: Always create branch to start a task
  • Auto Status Update: When adding branch to issue, automatically move to In Progress

📋 Task Execution Workflow

1. Task Start

ALWAYS follow this sequence:

  1. Create branch for the task

    git checkout -b feature/task-XX-task-name
    
  2. Add branch to issue on GitHub

    • Use script create-task-branch.ps1 or equivalent
    • Script must automatically move issue to "In Progress"
  3. Write tests FIRST (TDD - Red)

    • Follow rule test-driven-development-core.mdc
    • Tests must fail initially (Red)
  4. Implement minimal functionality (TDD - Green)

    • Make tests pass with minimal implementation
  5. Refactor safely (TDD - Refactor)

    • Improve code while keeping tests green

2. During Development

ALWAYS maintain:

  • Modularity: Each function/class with single responsibility
  • Tests passing: All tests must pass before commit
  • Clean Code: Follow clean-code-mandatory.mdc
  • Architecture: Respect project-architecture.mdc

NEVER:

  • ❌ Commit code without tests
  • ❌ Commit code with failing tests
  • ❌ Create non-modular code
  • ❌ Violate Clean Code principles

3. Task Completion

ALWAYS verify before marking as completed:

  • All tests pass?
  • Code follows Clean Code?
  • Code is modular?
  • Architecture respected?
  • Documentation updated (if necessary)?
  • Branch added to issue?
  • Issue moved to "In Progress" (or "Done" if completed)?

🔄 Integração com GitHub

Branch Creation Script

ALWAYS usar script que:

  1. Cria branch localmente
  2. Adiciona branch na issue do GitHub
  3. Automaticamente move issue para "In Progress"

Read the full file on GitHub · 275 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 · 275 lines · 1,894 tokens per session scan A 7179f834f55d

Subscribe to this mod's changes

task-execution is a cursor rule published in the GitHub repository Stramp/Lost-Mines-Phandelver (2 stars, last pushed 9mo ago), licensed MIT. It adds 1,894 tokens to every session, about $0.0095 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 2026-08-31.