Blast-radius analysis: prove a change is safe by running code, not writeups
Assess what a diff could break beyond the callers — find the one safety fact, climb the confidence ladder, prove it with a runnable script
- What
- Assess what a diff could break beyond the callers — find the one safety fact, climb the confidence ladder, prove it with a runnable script
- Cost
- Free
- Needs
- a diff or change to review and an environment where the agent can run code/scripts against the repo — the skill is a methodology, not software
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Selected by Skill Harbor — short listing (the repo states no license, so no content is reproduced): @cursor's blast-radius methodology for reviewing a diff you don't trust — don't hand back a writeup that merely sounds right; find the one or two facts the change's safety depends on, and for each fact climb the confidence ladder (you said so → you pointed at a real file:line → you walked the failure step by step → you ran real code → you reproduced it in the running app), stating honestly where each one stopped. Then prove the key fact with a small script or test that calls the real code and fails loud if you're wrong — and for big changes, run it as an arena (several models, merge the answers). Companion to the how/why skills in the same repository — not bundled here. Honest caveats: methodology only, no tooling — the agent must be able to run code against the repo; license not stated by the source repo — short listing with a link only, nothing copied. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Install
Prerequisites: a diff or change to review and an environment where the agent can run code/scripts against the repo — the skill is a methodology, not software Install "Blast-radius analysis: prove a change is safe by running code, not writeups" for me. It gives my agent @cursor's blast-radius methodology: read the change, find the one fact its safety depends on, climb the confidence ladder for each fact (said so → pointed at file:line → walked the failure → ran real code → reproduced in the running app), prove the key fact with a runnable script or test, and report risks, cleared items and the cheapest repro before merging. IMPORTANT: the repo states no license — fetch from the link only, and reproduce nothing beyond the link. Repository: https://github.com/cursor/plugins/blob/main/pstack/skills/blast-radius/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "blast-radius". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. hand the agent the diff to review; nothing else — it's a methodology). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.