Claude-Code on ROBOCO

Surprisingly, the Ralph Loop Is 9x Cheaper - The Economics of Context Caching

Sun, 26 Jul 2026 10:00:00 +0900

A single-session loop that just states a goal and runs until done finished the same task at one-ninth the cost of a plan-driven workflow. The secret isn’t the loop — it’s the cache.

Dohyun Jung - Principal Consultant, ROBOCO

The Ralph loop is a simple approach. You specify only the goal and the completion criteria, then let the agent iterate autonomously in a single session until it passes the completion check. No plan document, no task decomposition, no handoff notes between sessions. At first glance it looks unplanned and inefficient.

Does Karpathy's LLM Wiki Actually Work? A 72-Run Benchmark

Thu, 07 May 2026 11:00:00 +0900

“To keep agents from re-deriving everything every time, you need a compiled knowledge artifact.” — Andrej Karpathy, LLM Wiki (GitHub Gist, 2026-04)¹

Dohyun Jung - Principal Consultant, ROBOCO

TL;DR

We measured whether Andrej Karpathy’s LLM Wiki pattern (“don’t re-read every time; reuse knowledge compiled once”¹) is actually a win, using an 8-task × 3-technique × 3-repetition = 72-run benchmark in a 30-repository migration workspace.
LLM Wiki placed first on all three dimensions: tokens, time, and quality. Versus Vanilla, 54% fewer tokens and 39% less time (statistically a large effect, §4), with quality equal to Vanilla and better than Graphify.
Graphify (GraphRAG) is unsuitable as a default tool. Negligible token savings, the longest time, and the lowest quality.
That said, it’s not universal. Wiki wins decisively on tasks that synthesize multiple sources, but for tasks whose answer sits plainly in a single source (exhaustive grep, looking up a specific table), reading directly is faster and more accurate (§3).
On receiving these results, the project’s default context-retrieval tool was switched to LLM Wiki that same evening.

Technique	Tokens (avg)	Time (avg)	Quality (out of 25)
Vanilla (direct read/grep)	755K	167s	15.1
LLM Wiki	350K	101s	16.0
Graphify (GraphRAG)	617K	180s	13.6

Below is the experimental design and detailed numbers that support this conclusion.

A Close Look at Ruflo: What It Means to Layer Multi-Agent Orchestration onto Claude Code

Mon, 04 May 2026 11:30:00 +0900

How to design Claude Code workflows that learn from a team’s insights, not just a single project.

Dohyun Jung - Principal Consultant, ROBOCO

Use Claude Code for a month and the limits become clear. Context disappears along with the session, and breaking work apart and putting it back together is ultimately a human job. The bigger problem surfaces the moment you have multiple projects and multiple developers. The testing strategy learned on project A, the refactoring pattern discovered by developer B, the architectural judgment validated in repository C — none of it flows well between them. ruvnet/ruflo (formerly Claude Flow) targets exactly this gap. As of May 4, 2026, it has 39.4k stars and 4.5k forks on GitHub, with v3.6.27 as the latest release.¹² Ruflo aims to be an orchestration layer on top of Claude Code that adds roughly 100 specialized agents, HNSW vector memory, a plugin system, and Zero-Trust federation. This post lays out what Ruflo actually solves and what it does not, particularly from the standpoint of how to organically reuse the insights that multiple projects and multiple developers acquire.

A Token Management Strategy for Vibe Coding

Thu, 19 Mar 2026 09:00:00 +0900

Running out of tokens is rarely a model performance problem. It is usually a problem with how you operate your context.

Dohyun Jung - Principal Consultant, ROBOCO

Use a vibe coding tool like Claude Code, Codex, or Gemini long enough and the same symptoms start showing up. Responses slow down, constraints you already agreed on get forgotten, and the model starts touching files that have nothing to do with the task. We usually describe this as “running out of tokens,” but what is actually happening is closer to context pollution, or context rot.

Everything Claude Code vs Oh My ClaudeCode: A Comparison for Team and Enterprise Adoption

Tue, 27 Jan 2026 09:30:31 +0900

Everything Claude Code (ECC) hands developers a rich set of tools and guidelines. Its approach is to improve the output by making you follow optimal development habits and patterns. Oh My ClaudeCode (OMC), by contrast, automatically orchestrates multiple agents without any complicated setup. It focuses on getting results fast.

Dohyun Jung - Principal Consultant, ROBOCO

I covered each of these in two earlier posts, Everything Claude Code Distilled and Oh My ClaudeCode Distilled. In this post I compare the two tools currently generating the most buzz in the vibe coding community, to help you choose between them.

The Best Production-Grade, Cost-Effective Vibe Coding Tool from an Enterprise and Heavy-User Perspective (as of January 2026)

Sun, 25 Jan 2026 11:45:52 +0900

This piece was written as of January 2026. Pricing, usage limits, context windows, and plan structures change extremely fast, so I recommend reading it for the “principles and structure” rather than the specifics.

Dohyun Jung - Principal Consultant, ROBOCO

Vibe coding tools are entering the phase where “whatever you use, it more or less works.” So for enterprise users and heavy users, the question naturally shifts. It is no longer “which tool is the smartest,” but which tool you can use every day in production without hitting a bottleneck, at a cost that still makes sense.

Oh My Claude Code - The Plugin That Turns Claude Code Into a 'Team'

Wed, 21 Jan 2026 22:03:59 +0900

“Don’t learn Claude Code. Just use OMC.” – oh-my-claudecode README¹

Dohyun Jung - Principal Consultant, ROBOCO

oh-my-claudecode (OMC) is a plugin that layers “multi-agent orchestration” on top of Claude Code.¹ Its goal is to automatically activate the behaviors you need — planning, parallelization, persistent execution, research, design sensibility — using your natural-language request as the cue, so you never have to learn concepts like subagents, skills, and hooks one at a time.

Everything Claude Code: A Hackathon Winner's Recipe for an AI Dev Team

Tue, 20 Jan 2026 09:30:07 +0900

“If you want to bring AI onto the team, you have to design the process before the tools.” – Affaan Mustafa, winner of the Anthropic x Forum Ventures hackathon

Dohyun Jung - Principal Consultant, ROBOCO

Everything Claude Code is a collection of configurations that turns the Claude Code CLI into a virtual development team environment. A hackathon winner spent ten months refining these recipes while building an actual startup product, then gathered them all into one public repository; apply them and you can summon Claude as a “senior engineer + QA + architect.”¹ The repository is open for anyone to inspect on GitHub.

Vibe Coding and Security: True or False

Tue, 30 Dec 2025 10:01:21 +0900

Dohyun Jung - Principal Consultant, ROBOCO

These days, saying “I code with AI” is no longer special. It is already the new normal. Coding works — that is now a given — and today’s AI tools do far more than that in a business.

Even so, many companies hesitate at the adoption stage. The reason is always the same: security. Today I want to sort through the security concerns surrounding AI coding agents from an enterprise perspective — in particular Claude Code, the most widely chosen tool for production-level vibe coding — separating what is true from what is false.

Claude Code Deep Dive: How Is Claude Code Actually Built?

Tue, 25 Nov 2025 10:05:54 +0900

The world of meticulous prompt engineering hidden behind the “it just handles it for you” experience

Dohyun Jung - Principal Consultant, ROBOCO

Developers trying Claude Code for the first time often wonder, “How does it understand the context this well?” Claude Code doesn’t behave like a simple coding assistant; it acts like a colleague who has been on the project for a long time. The secret lies in a sophisticated system architecture in which more than 40 prompt fragments are assembled dynamically.