mcp-vkusvill: Skill for Claude Code

.claude/skills/feature-prompt-generator/SKILL.md

feature-prompt-generator is a skill for Claude Code from Bazilio-san/mcp-vkusvill. It costs 94 tokens per session (4,211 once invoked), scanned A, original, MIT.

A command-only skill that writes a detailed implementation prompt for Claude Code or another AI coding agent. It examines the target project so the prompt can describe the relevant code and requirements.

In plain words
What is it for?
Use it to turn a feature request into a self-contained coding prompt; it does not implement the feature or modify the repository.
Why use it?
It prepares a complete handoff for an agent when the operator wants the other agent to implement the feature rather than writing the code themselves.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Bazilio-san/mcp-vkusvill's own configuration. It tells Claude Code how to work on mcp-vkusvill itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-vkusvill configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import type { ToolWithHandler, ToolContext } from '../../_types_/tool.js';.

Reuse

Borrowing it

Nothing to install: this file belongs to Bazilio-san/mcp-vkusvill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Bazilio-san/mcp-vkusvill/master/.claude/skills/feature-prompt-generator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Bazilio-san/mcp-vkusvill

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 feature-prompt-generator

README.md
[![agentmods](https://agentmods.dev/badge/skills/bazilio-san/mcp-vkusvill/feature-prompt-generator/github.svg)](https://agentmods.dev/skills/bazilio-san/mcp-vkusvill/feature-prompt-generator)
Your own site
<a href="https://agentmods.dev/skills/bazilio-san/mcp-vkusvill/feature-prompt-generator"><img src="https://agentmods.dev/badge/skills/bazilio-san/mcp-vkusvill/feature-prompt-generator/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 feature-prompt-generator

Your own site · 80×15
<a href="https://agentmods.dev/skills/bazilio-san/mcp-vkusvill/feature-prompt-generator"><img src="https://agentmods.dev/badge/skills/bazilio-san/mcp-vkusvill/feature-prompt-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,211 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.
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 $0.00094 $0.04211
Opus 5 $0.00047 $0.02106
Sonnet 5 $0.00019 $0.00842
Haiku 4.5 $0.00009 $0.00421

Measured 12d ago against content hash f3de9e4d7102, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

feature-prompt-generator 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 12d 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.

- **Manual checks** — `yarn build && yarn start`, then HTTP (curl/PowerShell) or an MCP client;
.claude/skills/feature-prompt-generator/SKILL.md · 365 lines

How it starts

The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.

feature-prompt-generator — META-SKILL for generating prompts for an AI CLI

Essence

You do NOT write code. You generate a self-sufficient prompt for an AI CLI, which will then:

  • study the code itself,
  • design the solution itself,
  • implement it itself,
  • test it itself.

This is a META-skill (agent-building agent). Your output is a clean prompt, not an implementation. You do not touch any code in the target repository.

How to invoke

Command-only. The skill is never auto-invoked by the modeldisable-model-invocation is set to true. Runs solely when the operator explicitly calls it (e.g. /feature-prompt-generator or the equivalent UI invocation). Ignore any implicit triggers from phrasing in user messages.

When to use

  • The operator describes a feature/functionality but does not write code themselves.
  • A production-ready prompt is needed to hand off to Claude Code / another AI agent.

Core principles (Karpathy-style, think-before-code)

  1. Think before code. Architecture first, implementation second. Do not rush to code.
  2. Simplicity first. KISS / YAGNI / DRY — the minimal sufficient solution. No speculative features.
  3. Surgical changes. Touch only what is required. Do not "improve" adjacent code.
  4. Goal-driven. Every step has a verifiable success criterion.
  5. Anti-hallucination. Do not invent files, functions, or APIs. Only what actually exists in the code (verified via Read/Grep/Glob).
  6. Surface assumptions. Explicitly mark anything inferred on behalf of the operator as ASSUMPTION:.
  7. Ask, don't guess. If anything is ambiguous — stop, name the ambiguity, ask.

Input

The operator passes via $ARGUMENTS:

  • a free-form feature description, OR
  • a path to a file with the description (task.md, issue dump from a tracker, dialog excerpt).

If $ARGUMENTS is empty — request a feature description. Do not infer requirements on the operator's behalf. If the project uses an issue tracker (Jira/Linear/GitHub Issues) — ask for the task ID and reference it in the final prompt.

Read the full file on GitHub · 365 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. 12d ago First seen · 365 lines · 94 tokens per session scan A f3de9e4d7102

Subscribe to this mod's changes

feature-prompt-generator is a skill published in the GitHub repository Bazilio-san/mcp-vkusvill (1 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 4,211 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens