new-feature

new-feature is a skill for Claude Code from RamonBedin/mcp-game-deck. It costs 16 tokens per session (691 once invoked), scanned A, original, MIT.

A guided feature-planning skill for Unity game projects. It turns a feature idea into a user story, acceptance criteria, an implementation plan, and a file list after gathering the needed details.

In plain words
What is it for?
Use it to plan small, medium, or large features, review the relevant project structure and documentation, and break implementation into concrete tasks.
Why use it?
It removes guesswork before coding by clarifying what the feature must do, how large it is, and how it fits the existing project.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the mcp-game-deck plugin — 24 skills, 10 agents shipped together

Good fit Use it to plan small, medium, or large features, review the relevant project structure and documentation, and break implementation into concrete tasks.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add RamonBedin/mcp-game-deck
Claude Code
/plugin install mcp-game-deck

Made for: Claude Code.

Or install mcp-game-deck, the plugin that ships this one along with the rest of its 24 skills, 10 agents.

Wrote 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.

agentmods badge for new-feature

README.md
[![agentmods](https://agentmods.dev/badge/skills/ramonbedin/mcp-game-deck/new-feature/github.svg)](https://agentmods.dev/skills/ramonbedin/mcp-game-deck/new-feature)
Your own site
<a href="https://agentmods.dev/skills/ramonbedin/mcp-game-deck/new-feature"><img src="https://agentmods.dev/badge/skills/ramonbedin/mcp-game-deck/new-feature/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.

agentmods 80×15 button for new-feature

Your own site · 80×15
<a href="https://agentmods.dev/skills/ramonbedin/mcp-game-deck/new-feature"><img src="https://agentmods.dev/badge/skills/ramonbedin/mcp-game-deck/new-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 691 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00016 $0.00691
Opus 5 $0.00008 $0.00345
Sonnet 5 $0.00003 $0.00138
Haiku 4.5 $0.00002 $0.00069

Measured 9d ago against content hash 8d35966a7e7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

new-feature 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 9d 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.

Plugin~/skills/new-feature/SKILL.md · 79 lines

What it actually says

When this skill is invoked:

  1. Parse the feature name from the user's message. If the user wrote /new-feature InventorySystem, the name is InventorySystem. If no name was provided, ask for one.

  2. Ask for the following inputs before generating anything:

    • User story: "Describe the feature as a user story: 'As a player, I want to ... so that ...'"
    • Acceptance criteria: "What defines 'done'? List the conditions that must be true for this feature to be complete."
    • Scope: "What's the scope? (small = 1-2 files, medium = 3-6 files, large = 7+ files or cross-cutting)"

    Wait for the user to answer all three before proceeding.

  3. Scan the existing codebase to understand the current architecture:

    • Use Glob to find related scripts, prefabs, and ScriptableObjects
    • Use Grep to find references to related systems
    • Read relevant existing files to understand current patterns
  4. Read knowledge base docs relevant to the feature domain:

    • Always read ${CLAUDE_PLUGIN_ROOT}/knowledge/01-unity-project-architecture.md for project structure
    • Read additional KB docs based on feature type (e.g., doc 07 for gameplay, doc 08 for UI, doc 02 for data-driven systems)
  5. Generate the implementation plan with this structure:

    ## Feature Plan: [Feature Name]
    
    ### User Story
    [The user story from step 2]
    
    ### Acceptance Criteria
    [Numbered list from step 2]
    
    ### Architecture
    - **Pattern(s)**: [Which design patterns to use, from KB doc 03]
    - **Systems involved**: [New and existing systems]
    - **Data model**: [ScriptableObjects, serialized classes, or runtime data]
    - **Communication**: [Events, direct references, or message bus]
    
    ### Tasks
    [Ordered list of implementation tasks, each with]:
    - [ ] Task description
      - Files: `path/to/file.cs` (create / modify)
      - Depends on: [previous task number, if any]
    
    ### Files to Create
    | File | Purpose |
    |------|---------|
    | `path/to/NewFile.cs` | Description |
    
    ### Files to Modify
    | File | Change |
    |------|--------|
    | `path/to/ExistingFile.cs` | What to change |
    
    ### Complexity Estimate
    - **Scope**: [small / medium / large]
    - **Risk areas**: [What could go wrong]
    - **Suggested approach**: [Bottom-up, top-down, or spike-first]
    
    ### KB References
    - [List relevant KB docs with brief reason for each]
    
  6. Present the plan and ask if the user wants to proceed with implementation, adjust the plan, or save it as a design document.

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. 9d ago First seen · 79 lines · 16 tokens per session scan A 8d35966a7e7d

Subscribe to this mod's changes

new-feature is a skill published in the GitHub repository RamonBedin/mcp-game-deck (6 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 691 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 2026-08-31.