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:
Quick answer
Blast-radius analysis is a free Muse skill, a listing for reviewing a diff you do not trust: do not hand back a writeup that sounds right, find the one or two facts safety depends on, and for each fact climb the confidence ladder, stating where each stopped. Then prove the key fact with a script or test calling the code.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit ccb5507Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. 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://raw.githubusercontent.com/cursor/plugins/ccb5507cec1546dc88135c1139c811e6c59115ba/pstack/skills/blast-radius/SKILL.md Pinned version: install the code at commit ccb5507cec1546dc88135c1139c811e6c59115ba exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 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.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- ccb5507 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 18, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill 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 skill before installing it.