mtk-setup

mtk-setup is a skill for Claude Code from moberghr/mtk-agent-toolkit. It costs 0 tokens per session (3,347 once invoked), scanned A, original, MIT.

A single setup workflow for preparing or rechecking a repository, which is a project's code and related files. It can bootstrap a new setup, repeat an architecture audit, merge findings, refresh generated rules, or check for stale setup information.

In plain words
What is it for?
Use it when first preparing a repository, after major architectural changes, when combining findings from multiple repositories, or when checking generated configuration for drift.
Why use it?
It gathers project structure, technology choices, and architecture guidance in one place instead of requiring several separate setup steps.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the mtk plugin — 45 skills, 6 agents, 7 hooks, 1 MCP server shipped together

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 skills/moberghr/mtk-agent-toolkit/mtk-setup
Any agent
npx skills add moberghr/mtk-agent-toolkit --skill mtk-setup
Clone the repo
git clone --depth 1 https://github.com/moberghr/mtk-agent-toolkit

Made for: Claude Code.

Or install mtk, the plugin that ships this one along with the rest of its 45 skills, 6 agents, 7 hooks, 1 MCP server.

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 mtk-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/mtk-setup.svg)](https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/mtk-setup)
Your own site
<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/mtk-setup"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/mtk-setup.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,347 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 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 5.1 $0.00000 $0.03347
Opus 5 $0.00000 $0.01673
Sonnet 5 $0.00000 $0.00669
Haiku 4.5 $0.00000 $0.00335

Measured 5d ago against content hash a1bc70b06247, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mtk-setup scanned grade A with 2 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 5d 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.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

4. Otherwise, fall back to `find ~/.claude/plugins -maxdepth 8 -name "SKILL.md" -path "*/mtk/*/context-engineering/*" -type f 2>/dev/null | sort -V | tail -1 | sed 's|/.claude/skills/context-engineering/SKILL.md||'`. If

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

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

curl -fsSL "https://raw.githubusercontent.com/moberghr/coding-guidelines/$CURRENT_SHA/$FILE_PATH" | sha256sum | awk '{print $1}'
.claude/skills/mtk-setup/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MTK Setup — Unified Entry Point for Bootstrap and Audit

You are the single setup entry point for MTK. You dispatch to the right workflow skill based on the engineer's argument and the current state of the repo.

Overview

MTK distinguishes between two setup tasks:

  • Bootstrap (first-time setup): Detect tech stack, pull coding guidelines, audit the codebase once, generate CLAUDE.md, .claude/tech-stack, and .claude/references/architecture-principles.md. This is the one-time preparation.
  • Re-audit: Re-run the architectural audit only. Regenerates .claude/references/architecture-principles.md (and conventions.md) to reflect current reality. Use after significant architectural change.
  • Merge: Unify architecture audits from multiple repos (e.g., a team hub repo that aggregates payfac, collection-system, etc.) into a single team-wide document.
  • Refresh: Drift-scoped refresh of ALL generated rules and findings (architecture-principles, conventions, detected-tools, reference pruning, AGENTS.md/tool configs, indexes) — not just the audit doc. --check is the CI gate that reports staleness without writing anything.
  • Converge: Inverse of refresh — code is judged against the agreed architecture-principles.md/conventions.md, and violations are reported as graded work items (blocking/flag/note), never auto-fixed.

When To Use

  • First time onboarding a repo → run /mtk-setup with no flags.
  • Architecture has drifted and you want architecture-principles.md refreshed → /mtk-setup --audit.
  • You have audit files from multiple repos in .claude/references/audits/ and want one unified doc → /mtk-setup --merge.
  • Generated docs (architecture-principles, conventions, detected-tools, AGENTS.md, indexes) have drifted, or you just merged significant changes → /mtk-setup --refresh (add --dry-run to preview first).
  • CI or a quick staleness question ("are the generated docs still accurate?") → /mtk-setup --check.
  • You want to know where the code has drifted from the agreed architecture-principles.md/conventions.md, graded as reviewable work items → /mtk-setup --converge.

Read the full file on GitHub · 150 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. 5d ago First seen · 150 lines · 0 tokens per session scan A a1bc70b06247

Subscribe to this mod's changes

mtk-setup is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (7 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,347 tokens. A static security scan graded it A with 2 findings (reads agent configuration directories, 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens