Hi! I am Ricardo Sueiras, leading SDLC transformation at Indicium AI. That means I get to work with customers and help them understand how to use agentic AI to build software. New tools, practices and opinions turn up every week, and Build without Limits cuts through the noise. In each edition we put together a short, curated briefing on what's worth reading, watching and worth trying. You can skim it in five minutes and dive deeper wherever something catches your eye.
Top of Mind
State of agent skills is a report from Vercel that looks at the state of agent skills, drawing from the data they have amassed from hosting the skills.sh registry (one of a few that are out there). Essential reading.
Must reads this week
git workstree gotchas is required reading for those of us who run parallel sessions within the same repo. Some of the points raised in this post will be familiar with folk, but there were enough new ones to make this post interesting.
Linux Foundation published its research into Developer Experience that contains some nice check lists that you can review/use as you look into what is, and how to measure developer experience. Why does this matter? SDLC transformation using agentic AI is a key driver for improving developer experience, and many organisations are now beginning to spin up developer experience teams where agentic AI tooling and governance sit.
Getting started with Claude Code mods is the official launch post that walks you through what Claude Code mods are and how to build one. Beginning to see a few folk doing some cool things with this, so check this out.
Watch this
Fixing the PR Bottleneck This week I spent some time on my commute watching the latest Matt Pocock knowledge drop on how to think and approach the review bottleneck in agentic engineering. Don't want to give too much away, but I think there are some really good perspectives here.
Tools to try out
Third-party tools links are provided as-is. They belong to their owners, follow their own licenses, and are used at your own risk.
Codebase-memory-mcp is a local MCP server that turns your repo into a searchable knowledge graph of functions, calls, routes and dependencies. AI coding agents can then answer questions like "what calls this?" or "what breaks if I change this?" with one query, instead of reading through files one at a time. This is really handy if you are tackling code modernisation or supporting legacy tech stacks, something that we at Indicium AI are increasingly helping customers with.
Shipreel is a neat tool that helps you create visuals (video), turning a pull request into a short narrated walkthrough video. It uses your harness to read the diff, write a story, draw the diagrams, record the real app if the change has a UI, and then render a compact MP4, about two and a half minutes by default, with captions, crossfade cuts and an ambient music bed.
From the field
Should workers be paid for AI skills? is a super interesting post that piqued my interest given recent customer meetings that have flagged the topic of how much is the premium for AI competent engineers, and what flight risk do they present to an organisation if they train their existing engineers in AI. Are you seeing this in your organisation?
If you enjoyed this, then remember to subscribe to the IndiciumAI blog so that you can keep up to date with future editions of this newsletter, as well as other great content that technologists at IndiciumAI will publish.
Top comments (0)