Better Agent Tools Made Code Review Worse

More from Claude Code Cast All episodes →

1. 

   28 Aug 2026 · 21 min

   Same Model, 70x the Tokens—Your Harness Sets the Bill

   Three benchmarking efforts ran an identical model through different coding-agent harnesses and reported token use varying seventy-fold. Fictional AI hosts Alex and Sam explain where harness tokens actually go, why Anthropic's Files API saves time but not money, and how to measure tokens-per-completed-task on your own repository before you switch tools.

2. 

   25 Aug 2026 · 19 min

   Your Coding Agent Passed the Benchmark—Then Failed the Refactor

   Most coding-agent benchmarks reward contained tasks, but real repositories demand changes across boundaries, tests, migrations, and documentation. Fictional AI hosts Alex and Sam show how to run a five-part refactor trial that exposes whether an agent can preserve architecture—not merely produce a passing patch.

3. 

   14 Aug 2026 · 18 min

   Passing Tests Isn't Enough for Your Next Coding Agent

   Passing CI can still leave code that slows down—or misleads—the next AI agent. Fictional AI hosts Alex and Sam use this week’s debate about Go and agent-friendly engineering to build a practical machine-legibility checklist, a handoff receipt, and one pro tip you can try in your next coding session.

4. 

   2 Aug 2026 · 21 min

   Your OpenClaw Updates Need a Canary, Not Courage

   OpenClaw’s release feed is moving faster than its labels can explain, so blind auto-update is a bad personal-automation strategy. Cleo and Dev build a Release Sentinel canary, keep telemetry local, and show how stateless MCP can shrink the trust you carry between jobs.

5. 

   24 Jul 2026 · 20 min

   Claude Code Changed Engines—Your Evals Just Broke

   Claude Code’s move to a new Bun runtime is a reminder that your coding agent has a software supply chain too. Alex and Sam unpack runtime drift, model routers, reverse-engineering with agents, and a five-minute reproducibility receipt you can add to your next session.

6. 

   3 Jul 2026 · 19 min

   Your AI Coding Benchmarks Are Lying To You

   This week, Alex and Sam look at why benchmark wins are a bad way to choose coding tools, what Godot's coding-agent ban reveals about mentorship, and a simple workflow for making agents show their work. If your team is still asking "which model scored highest?", this episode gives you a better test.

7. 

   26 Jun 2026 · 18 min

   The Tiny Local Model That Changes Your Agent Budget

   Small, local models are suddenly good enough for real agent chores, but the win is not replacing your smartest model. Cleo and Dev unpack lightweight extraction models, model-routing memory, browser-safe harnesses, and the OpenClaw skill that sends cheap tasks to local models while reserving expensive intelligence for the moments that matter.

8. 

   19 Jun 2026 · 19 min

   Your Coding Agent Needs a Bouncer Now

   AI coding agents are getting longer runs, more context, and more ways to touch production workflows, but this week made the real bottleneck obvious: authorization. Alex and Sam unpack MCP's missing enterprise auth layer, confused-deputy risks, Copilot context handling, and the verification habits that keep an agent from helping itself to the wrong keys.

9. 

   17 Jun 2026 · 12 min

   Verification Is Now Your Coding Agent Bottleneck

   Coding agents are getting better at long runs, but this week's news points at the real limit: proof. Alex and Sam unpack agent loops, Stack Overflow for Agents, Copilot CLI delegation, local-model coding, and the verification habits that keep a confident agent from shipping the wrong thing.

10. 

    5 Jun 2026 · 17 min

    Cursor's Tokenomics Reckoning Hits Every Coding Agent

    Coding agents are no longer just a workflow story; they are a cost, context, and control story. Alex and Sam unpack Cursor's pricing reset, Uber capping Claude Code usage, GitHub's agent-native desktop app, Microsoft Rayfin, and the spending harness every team needs before the next invoice arrives.