new-feature-design

new-feature-design is a skill for Claude Code from agentic-community/mcp-gateway-registry. It costs 118 tokens per session (15,514 once invoked), scanned A, original, Apache-2.0.

A design workflow for turning a requested MCP Gateway Registry feature into implementation documents. It covers a GitHub issue, a low-level design, expert review, and a testing plan.

In plain words
What is it for?
Use it to design a new registry feature from a description or GitHub issue, examine the codebase, and produce structured files in the project’s .scratchpad folder.
Why use it?
It gives developers a shared technical description before coding begins, including requirements, design decisions, review feedback, and planned checks.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code; built for roo code.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **REQUIRED: theory alignment.** Read [Theory of the System](../../../docs/design/theory-of-the-system.md).

Good fit Use it to design a new registry feature from a description or GitHub issue, examine the codebase, and produce structured files in the project’s .scratchpad folder.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/agentic-community/mcp-gateway-registry
agentmods
npx agentmods add skills/agentic-community/mcp-gateway-registry/new-feature-design

Made for: Claude Code.

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-design

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/agentic-community/mcp-gateway-registry/new-feature-design"><img src="https://agentmods.dev/badge/skills/agentic-community/mcp-gateway-registry/new-feature-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 15,514 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 718
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 1699
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Data Exfiltration · line 1397
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 1452
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 1490
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 1741
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00118 $0.15514
Opus 5 $0.00059 $0.07757
Sonnet 5 $0.00024 $0.03103
Haiku 4.5 $0.00012 $0.01551

Measured 11d ago against content hash bbf51e6f6fec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

new-feature-design scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: "Design and document new features with GitHub issue, low-level design (LLD), expert review, and testing plan. Creates structured documentation in .scratchpad/ with issue spec, technical design with diagrams
.claude/skills/new-feature-design/SKILL.md · 1,924 lines

How it starts

The opening of the file, as written. The whole thing — 1,924 lines — stays where its author put it; the contents beside it link to each section on GitHub.

New Feature Design Skill

Use this skill when the user wants to design a new feature for the MCP Gateway Registry. This skill creates comprehensive design documentation that enables entry-level developers to implement the feature.

Input Modes

This skill supports two input modes:

  1. User Description Mode - User describes the feature they want to design
  2. GitHub Issue URL Mode - User provides a URL to an existing GitHub issue

Detecting Input Mode

When the user invokes this skill:

  • If they provide a GitHub issue URL (e.g., https://github.com/owner/repo/issues/123), use GitHub Issue URL Mode
  • Otherwise, use User Description Mode

Workflow

User Description Mode Workflow

  1. Gather Requirements - Ask clarifying questions about the feature
  2. Quick Codebase Review - Explore the codebase to understand structure
  3. Create Design Folder - Create .scratchpad/{feature-name}/ directory
  4. Write GitHub Issue - Create github-issue.md for issue creation
  5. Deep Codebase Analysis - Thoroughly explore relevant code
  6. Write Low-Level Design - Create lld.md with technical details
  7. Expert Review - Create review.md with multi-persona feedback
  8. Write Testing Plan - Create testing.md with functional, backwards-compat, UX, ECS, and E2E tests
  9. Present Summary & Seek Guidance - Present findings and ask for direction

GitHub Issue URL Mode Workflow

  1. Fetch GitHub Issue - Retrieve issue content using gh CLI
  2. Analyze Issue Content - Extract requirements, design elements, and context
  3. Quick Codebase Review - Explore the codebase to understand structure
  4. Create Design Folder - Create .scratchpad/issue-{number}/ directory (e.g., issue-500 for GitHub issue #500)
  5. Summarize Existing Issue - Create github-issue.md summarizing the existing issue
  6. Clarify Requirements - Ask user about any gaps or ambiguities found
  7. Deep Codebase Analysis - Thoroughly explore relevant code
  8. Write Low-Level Design - Create lld.md with technical details
  9. Expert Review - Create review.md with multi-persona feedback
  10. Write Testing Plan - Create testing.md with functional, backwards-compat, UX, ECS, and E2E tests
  11. Present Summary & Seek Guidance - Present findings and ask for direction

Read the full file on GitHub · 1,924 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. 11d ago First seen · 1,924 lines · 118 tokens per session scan A bbf51e6f6fec

Subscribe to this mod's changes

new-feature-design is a skill published in the GitHub repository agentic-community/mcp-gateway-registry (909 stars, last pushed today), licensed Apache-2.0. It adds 118 tokens to every session and 15,514 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

brand-landingpage

Brand-first landing page designer — runs a brand-identity interview (colors, typography, shape language), then generates and iterates on a polished landing page via Stitch with deployment-ready HTML. Use when the user asks to create, design, or build a landing page, homepage, or marketing page and has no established…

wshobson/agents · 112 tokens

wcag-audit-patterns

Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance. Use when auditing websites for accessibility, fixing WCAG violations, or implementing accessible design patterns.

wshobson/agents · 45 tokens

sage-review

Deep, platform-neutral code review for PRs and CRs in ONE thorough single pass — design reasoning (Problem Worth Solving & Solution Fit) as one dimension alongside the 9 code-level dimensions, with chain-of-consequences, self-critique, and draft-only comments. The single app-owned source of truth.

kirodotdev/KiroCrew · 68 tokens

design-critique

Run a heuristic evaluation of a UI design (image, HTML, Figma, URL, or flow) the way an experienced designer would. Evaluates 4 categories (Visual & hierarchy, Usability & interaction, Accessibility, Content) using recognized frameworks, NN/g 0-4 severity, and evaluability-aware prioritization that never judges what…

kirodotdev/KiroCrew · 131 tokens

theme-pack-authoring

Build, validate, and install Kiro Crew theme packs -- pack anatomy, the 56-variable palette, role-tagged fonts, the overrides.css allowlist (what installs vs what actually renders), and the install-verify cycle. Use when the user wants to create or edit a theme pack.

kirodotdev/KiroCrew · 64 tokens

image-authoring

Author images and diagrams as code — SVG, Pillow, Excalidraw, mermaid. Load when asked to draw, illustrate, or make an image, icon, logo, poster, or diagram.

kirodotdev/KiroCrew · 45 tokens