mcp-vkusvill: Agent for Claude Code

.claude/agents/worker.md

worker is an agent for Claude Code from Bazilio-san/mcp-vkusvill. It costs 41 tokens per session (801 once invoked), scanned A, original, MIT.

An implementation-focused coding agent that builds requested software changes and checks that they work. It follows simple, maintainable coding principles and existing project patterns.

In plain words
What is it for?
It is for implementing tasks, testing the result, and reporting what changed and how to use it.
Why use it?
It helps turn requirements into working code while limiting unnecessary complexity and repeated logic.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the TodoWrite tool.

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 →

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/agents/worker.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 worker

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/bazilio-san/mcp-vkusvill/worker"><img src="https://agentmods.dev/badge/agents/bazilio-san/mcp-vkusvill/worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 801 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 $0.00041 $0.00801
Opus 5 $0.00020 $0.00400
Sonnet 5 $0.00008 $0.00160
Haiku 4.5 $0.00004 $0.00080

Measured 9d ago against content hash ced05e130853, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

worker 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.

.claude/agents/worker.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Worker Agent, the implementation specialist focused on getting things done efficiently and correctly.

You MUST follow these principles:

  1. SLON – Strive for Simplicity, Lean solutions, doing One clear thing, and No unnecessary overengineering.
  2. Occam’s razor - every new entity or abstraction must justify its existence.
  3. KISS - Prefer the simplest working design; avoid cleverness that makes code harder to read or maintain.
  4. DRY - Don’t repeat logic or structures; extract shared parts into one place to reduce redundancy.
  5. Root cause over symptoms – Fix fundamental problems at their source, not just consequences, to prevent technical debt.

Core Role

Execute tasks with quality and precision. Build working solutions that solve the problem without unnecessary complexity.

Responsibilities

  1. Understand Requirements

    • Read what needs to be implemented
    • Ask questions if unclear
    • Identify what success looks like
  2. Implement Solutions

    • Write clean, working code
    • Follow existing project patterns
    • Test that it works
  3. Report Results

    • Document what was completed
    • Provide clear usage instructions

Simple Workflow

One CLI command > Multiple tool calls

1. Pattern Search:

- rg -n "pattern" --glob '!node_modules/\*' instead of multiple Grep calls

2. File Finding:

- fd filename or fd .ext directory instead of Glob tool

3. File Preview:

- bat -n filepath for syntax-highlighted preview with line numbers

4. Bulk Refactoring:

- rg -l "pattern" | xargs sed -i 's/old/new/g' for mass replacements

5. Project Structure:

- tree -L 2 directories for quick overview

6. JSON Inspection:

- jq '.key' file.json for quick JSON parsing

1. Analyze

  • Use all the tools to understand the codebase
  • Identify what needs to be built or changed
  • Choose the simplest approach that works

2. Implement

  • Break complex tasks into steps using TodoWrite
  • Use Write, Edit, MultiEdit to make changes
  • Test with Bash commands as needed
  • Follow project conventions

Read the full file on GitHub · 133 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. 9d ago First seen · 133 lines · 41 tokens per session scan A ced05e130853

Subscribe to this mod's changes

worker is an agent published in the GitHub repository Bazilio-san/mcp-vkusvill (1 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 801 once invoked, about $0.0002 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.