feature-development

A complete workflow for developing a feature from a Jira ticket to a pull request. It includes planning, coding, testing, review, and final checks.

In plain words
What is it for?
Use it to pick up a ticket, understand its requirements, plan files and components, implement the feature, run tests, obtain developer and specialist reviews, and prepare the pull request.
Why use it?
It gives a team a repeatable process for turning a ticket into tested, reviewed code.

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/kubev2v/forklift-console-plugin/feature-development
Clone the repo
git clone --depth 1 https://github.com/kubev2v/forklift-console-plugin

Made for: Cursor.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,344 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00010 $0.01344
Opus 5 $0.00005 $0.00672
Sonnet 5 $0.00002 $0.00269
Haiku 4.5 $0.00001 $0.00134

Measured 2d ago against content hash aadadad0957f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-development 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.

.cursor/rules/workflows/feature-development.mdc · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Development Workflow

Invoke with: "start a new feature", "work on MTV-XXX end to end", "full development workflow"

This is the complete workflow from picking up a Jira ticket to submitting a PR.


1. Workflow Overview

1. PICK UP TICKET
   "Start working on MTV-1885"
   Fetch ticket, understand requirements, plan approach

2. PLAN IMPLEMENTATION
   "Help me plan the implementation"
   Identify files to modify, components to create

3. IMPLEMENT
   "Create the component", "Add the feature"
   Write code following project standards (AGENTS.md)

4. TEST
   "Test my changes", "Add unit tests"
   Unit tests, interactive testing with Playwright

5. REVIEW
   "Review my code"
   Multi-perspective review (dev, UX, QE, security, Forklift expert)

6. PREPARE PR
   "Prepare this for PR"
   Quality checks, PR description, update Jira

2. Phase 1: Pick Up Ticket

Get the Ticket

"Start working on MTV-1885"

I will:

  1. Fetch ticket details from Jira
  2. Summarize requirements - what needs to be built
  3. Identify acceptance criteria - definition of done
  4. Check dependencies - blockers, related tickets

Understand the Context

  • Epic/parent story
  • Related tickets and comments
  • Attached mockups or designs

3. Phase 2: Plan Implementation

Identify Code Changes

"Help me plan how to implement this"

I will:

  1. Find relevant existing code - similar components, utilities
  2. Identify files to modify - which components are affected
  3. Suggest new files needed - new components, hooks, utils
  4. Recommend approach - how to structure the solution

Consider Architecture

  • Does this fit existing patterns?
  • Should this be a reusable component?
  • What's the impact on other features?
  • Which provider types are affected?

4. Phase 3: Implement

Create Components

Following new-component.mdc workflow:

  • Proper folder structure
  • TypeScript types (using type, not interface)
  • SCSS styles with BEM
  • Translation support (useForkliftTranslation)
  • Accessibility requirements

Read the full file on GitHub · 237 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 · 237 lines · 10 tokens per session scan A aadadad0957f

Subscribe to this mod's changes

feature-development is a cursor rule published in the GitHub repository kubev2v/forklift-console-plugin (11 stars, last pushed 2d ago), licensed Apache-2.0. It adds 10 tokens to every session and 1,344 once invoked, about $0.0001 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.