From ac175b86f0f536ad09f5d62e4c61446624c481c2 Mon Sep 17 00:00:00 2001 From: yifu zuo Date: Thu, 29 Oct 2026 12:31:56 -0500 Subject: [PATCH] feat(blast-radius): add blast-radius guardrail skill plugin Finds what a change could break beyond the diff and proves the one fact it is safe because of by running real code instead of writing it up. Adapted from the pstack skills (MIT, (c) Lauren Tan, https://github.com/cursor/plugins), Cursor-specific tooling removed. --- .factory-plugin/marketplace.json | 6 +++ README.md | 8 +++ .../blast-radius/.factory-plugin/plugin.json | 8 +++ plugins/blast-radius/README.md | 9 ++++ .../blast-radius/skills/blast-radius/SKILL.md | 49 +++++++++++++++++++ skills/blast-radius | 1 + 6 files changed, 81 insertions(+) create mode 100644 plugins/blast-radius/.factory-plugin/plugin.json create mode 100644 plugins/blast-radius/README.md create mode 100644 plugins/blast-radius/skills/blast-radius/SKILL.md create mode 120000 skills/blast-radius diff --git a/.factory-plugin/marketplace.json b/.factory-plugin/marketplace.json index 4282159..dc7791c 100644 --- a/.factory-plugin/marketplace.json +++ b/.factory-plugin/marketplace.json @@ -53,6 +53,12 @@ "description": "Pull request lifecycle skills: create PRs with consistent conventions and follow up on them until merge-ready", "source": "./plugins/code-review", "category": "productivity" + }, + { + "name": "blast-radius", + "description": "Find what a change could break beyond the diff and prove the one fact it's safe because of by running real code", + "source": "./plugins/blast-radius", + "category": "quality" } ] } diff --git a/README.md b/README.md index 9793470..d8585b5 100644 --- a/README.md +++ b/README.md @@ -96,6 +96,14 @@ Skills for continuous learning and improvement. Autonomous experiment loop for optimization research. Try an idea, measure it, keep what works, discard what doesn't, repeat. Works standalone or as a mission worker. +### blast-radius + +Find what a change could break beyond the diff, and prove the one fact it's safe because of by running real code. + +**Skills:** + +- `blast-radius` - Assess blast radius before it ships, with the safety fact proven by a run, not a writeup + ## Plugin Structure Each plugin follows the Factory plugin format: diff --git a/plugins/blast-radius/.factory-plugin/plugin.json b/plugins/blast-radius/.factory-plugin/plugin.json new file mode 100644 index 0000000..7b95b18 --- /dev/null +++ b/plugins/blast-radius/.factory-plugin/plugin.json @@ -0,0 +1,8 @@ +{ + "name": "blast-radius", + "description": "Find what a change could break beyond the diff and prove the one fact it's safe because of by running real code", + "author": { + "name": "yifu zuo", + "email": "yzuo.2019@gmail.com" + } +} diff --git a/plugins/blast-radius/README.md b/plugins/blast-radius/README.md new file mode 100644 index 0000000..14536e6 --- /dev/null +++ b/plugins/blast-radius/README.md @@ -0,0 +1,9 @@ +# blast-radius + +Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code. + +**Skills:** + +- `blast-radius` - Assess what a change could break beyond the diff, with the one safety fact proven by a run, not a writeup + +Adapted from the pstack skills by Lauren Tan ([cursor/plugins](https://github.com/cursor/plugins), MIT License), with Cursor-specific tooling removed and Droid conventions applied. diff --git a/plugins/blast-radius/skills/blast-radius/SKILL.md b/plugins/blast-radius/skills/blast-radius/SKILL.md new file mode 100644 index 0000000..e4b5e7f --- /dev/null +++ b/plugins/blast-radius/skills/blast-radius/SKILL.md @@ -0,0 +1,49 @@ +--- +name: blast-radius +description: "Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', or reviewing a small diff you don't trust." +--- + +# 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. + +Code review tells you what a change does. 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. + +1. You said so. Worthless on its own. +2. You pointed at the line. A real `file:line`, or the library's own source. +3. You showed the bad case can't happen. You walked the failure step by step and it doesn't reach. +4. You ran it. A script or test that calls the real code and fails loud if you're wrong. +5. You reproduced it in the running app. + +Step 4 is usually one small script that imports the same library the app ships and calls the exact function you're worried about. + +## Steps + +1. Read the change. The diff, the symbols it adds, changes, and deletes, and what it now does differently, including the part the diff doesn't spell out. Pull the PR and its commits. +2. Find the one fact it's safe because of. Most changes that look risky are safe because of a single fact, like "this call only drops already-dead cache entries and does nothing else". Find that fact. If it holds, most risky cases are cleared at once. Spend your time here, not on a long list of maybes. +3. Look where grep stops. Read the source of the library you call, and check its pinned version and any local patch. Work out when things run: microtasks, unmount and teardown, Solid versus React. Follow what a symbol search misses: the JSON an API returns, a DB column, a wire format, another language reading the same bytes, a feature flag, code three hops downstream. +4. Be honest about each risk. Give it a real chance of happening and a real cost if it does. Keep the risks you confirmed. List the ones you checked and cleared separately. Cite a real `file:line`; a search that finds nothing is still an answer, and never make up a caller or an API. +5. Prove the one fact. Write a script or test that runs the real code, run it, and paste what happened. +6. For a big or wide change, ask more than one model the same question (fan out subagents when you can) and merge the answers. Different models catch different real bugs. + +## What to hand back + +- **What it does.** What changed, including the part that isn't obvious. +- **The one fact it's safe because of.** State it, say which step you got it to, and show the proof. If you couldn't prove it, write unproven. +- **Risks.** Each names how it breaks, the `file:line`, how likely and how bad, and how to check. Paste the proof for the ones that matter. +- **Cleared.** What you checked and why it's fine. +- **Before you merge.** The cheapest test or repro that catches the real bug, including the script you wrote. + +Write it plainly, cite real code, and strip anything private before it goes anywhere public. + +**Reply:** the writeup above, with the one safety fact either proven or marked unproven. diff --git a/skills/blast-radius b/skills/blast-radius new file mode 120000 index 0000000..8e107a5 --- /dev/null +++ b/skills/blast-radius @@ -0,0 +1 @@ +../plugins/blast-radius/skills/blast-radius \ No newline at end of file