Tool-Agnostic on Tokenise

Gate the NuGet packages your agent adds: a lock file, the audit, and a short script for what advisories miss

Sun, 01 Nov 2026 07:04:00 +0000

An agent is asked to add retry logic and comes back with a green build and a diff that includes one new line in a .csproj: a PackageReference to something with a plausible name. The build passes because the package exists. Nobody asks who published it, when, or what else came with it, because a 40-file diff has better places for the eye to go.

Run your README's code blocks as Vitest tests so an agent can't leave the docs lying

Sat, 31 Oct 2026 16:04:00 +0000

An agent renames a function, updates every caller, fixes the tests, and ships a clean diff. The README still shows the old name. Nothing failed, because nothing reads the README except the next developer, who pastes the example, gets a compile error and loses ten minutes deciding whether to trust anything else on the page.

Move to TypeScript 7 in two passes: get clean on 6.0, then diff the two compilers

Sat, 31 Oct 2026 11:07:00 +0000

A project that compiles cleanly on TypeScript 6.0 can still fail on 7.0, and the reason is almost always one line in tsconfig.json. 7.0 turned the options 6.0 deprecated into hard errors, changed what rootDir and types default to, and shipped without a programmatic API. None of that is hard to fix. The risk is finding it one CI failure at a time, or handing the whole thing to an agent that “fixes” errors by loosening the config.

Check an agent's architecture summary against the import graph before you trust it

Sat, 31 Oct 2026 07:03:00 +0000

Day one in a repo you didn’t write, and the agent’s tour reads beautifully. “The entry point wires up a core client, which delegates to utility modules and throws typed errors.” Every sentence sounds right. Some of them aren’t, and nothing in the prose tells you which.

What the AI productivity studies measured, and what to measure on your own team

Fri, 30 Oct 2026 16:02:00 +0000

Three sources get quoted whenever someone argues about whether AI makes a team faster: a METR trial, the DORA report and the Stack Overflow survey. They measure different things, and only one of them tried to time anything.

Move a JavaScript module to strict TypeScript one flag at a time, with the compiler and your tests as the gate

Fri, 30 Oct 2026 11:05:00 +0000

A 400-line JavaScript module has to become TypeScript, and the obvious plan is to rename every file to .ts, flip strict on and let an agent grind through the errors. That plan produces a diff nobody can review. Hundreds of errors arrive at once, the fastest way to silence them is any or a cast, and somewhere in the pile a “fix” quietly changes what the function returns.

Write the OpenAPI file first, then let the compiler and a short test catch every place the agent drifts from it

Fri, 30 Oct 2026 07:07:00 +0000

The ticket says the invoice response has a totalMinor field. The backend developer’s agent returns total, because that read more naturally to it. The frontend developer’s agent calls invoice.totalMinor, divides by 100 and renders NaN. Both pull requests are green. Each side’s tests were written by the side that made the mistake, so each side agreed with itself.

Build a feature from a spec, tests first, then let Stryker.NET list what the spec forgot

Thu, 29 Oct 2026 23:12:00 +0000

A pricing rule arrives as a ticket: promo codes, a cap on one of them, a minimum spend on another, and “obviously only one code per order”. The agent writes the endpoint in a minute. It looks right. Two weeks later a customer with a 30.00 basket gets told the minimum isn’t met, because the check says <= where the ticket meant <, and nobody can say which of the two the ticket actually meant.