← All topics

Mr.D / Engineering topics

Mr.D mascot exploring engineering

Open source

Open-source tools by D. Klincharski, built around repeated engineering work: setting up a workstation, deploying infrastructure, checking cloud accounts, and finding failed pipelines. Browse the repositories alongside notes and experiments explaining the work behind them.

About D. Klincharski

Articles / Experiments

Notes from the work.

01 Oct 11, 2026 Inside ReelHive: an agent harness built with Strands GraphHow six agent roles, Strands graphs, production scripts, and quality gates work together to turn a brief into a narrated video in ReelHive. Technical blog · 7 min 02 Oct 11, 2026 What building a video agent taught me about agent harnessesBuilding a video pipeline with Strands Graph changed where I put the effort: state, checks, recovery and approvals. Why I think agent harnesses come next. Journal · 6 min 03 Sep 29, 2026 Start compliant: a Terraform Fargate baseline that passes the scanner on day oneHow the open-source Terraform ECS Fargate starter now ships the controls WardBee by ScanComb checks for, so new services begin with evidence instead of a remediation backlog. Technical blog · 6 min 04 Sep 09, 2026 I scanned an AWS account with 4 open-source FinOps tools. Here's what each one missed.Infracost, Komiser, Cloud Custodian and OpenCost, run against the same account. Each found something the others could not see, and all four shared the same blind spots. Journal · 6 min 05 Aug 26, 2026 How I audit an AWS account with Prowler, ScoutSuite and SteampipeA practical walkthrough of the three open-source tools I reach for when someone hands me an unfamiliar AWS account and asks "is this okay?" Journal · 5 min 06 Jul 28, 2026 MCP v2 Migration Guide: What Changed and Should You Upgrade?A practical MCP v2 migration guide covering SDK changes, the stateless 2026 protocol, compatibility risks, and when upgrading is worth it. Technical blog · 10 min 07 Jul 28, 2026 Should Every MCP Server Ship with an Agent Skill?An MCP server must stand on its own. Learn when an optional agent skill adds real value—and when it only hides a poor interface. Technical blog · 10 min 08 Jul 28, 2026 15 Rules for Designing Token-Efficient MCP APIs for AI AgentsFifteen practical rules for MCP APIs that reduce tool calls, context bloat, latency, and cost without starving AI agents of useful data. Technical blog · 14 min 09 Jul 23, 2026 The small tools we built for ourselves and decided to give awayOur open-source toolbox came out of daily annoyances, not a product plan. Here's what each tool does and why we use it ourselves. Technical blog · 3 min

Explore by topic