Blast Radius

When you're staring at a diff wondering what it could break three files away, this skill finds the actual blast radius, not just the obvious callers. It pushes you past grep to the real breakage points: the JSON format another service reads, the teardown order that matters, the library behavior the diff assumes. The core idea is sharp: find the one fact the change is safe because of, then prove it by running code instead of writing it up. You get a hierarchy of certainty from "you said so" (worthless) to "you ran it" (a script that imports the real library and fails if you're wrong). Works solo or runs multiple models in an arena for big changes.

skills.sh installs: 7.1K
GitHub stars: 15.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add cursor/plugins --skill blast-radius --agent claude-code

Installs into .claude/skills of the current project.

Files

Blast radius

Find what a change breaks somewhere else, before it ships. Use for "blast radius of X", "what could this break", or reviewing a small diff you don't trust yet.

Companion to how and why. how tells you what the code does. why tells you why it's shaped that way. Blast radius tells you what it breaks somewhere else.

Listing the callers is not the job. The agent can grep those in a second. The job is the breakage grep won't show you.

Don't trust your own writeup

A blast-radius writeup that sounds right is worthless. It reads as convincing whether or not it's true. So don't hand back the writeup. Find the one or two facts the whole thing depends on and prove them by running code.

How sure are you

For each fact the change's safety depends on, get it as far down this list as is cheap, and say where it stopped.

You said so. Worthless on its own.
You pointed at the line. A real file:line, or the library's own source.
You showed the bad case can't happen. You walked the failure step by step and it doesn't reach.
You ran it. A script or test that calls the real code and fails loud if you're wrong.
You reproduced it in the running app.

SKILL.md on GitHub