blast-radius

Determine what code, behavior, consumers, tests, schemas, services, and integrations could be affected by changing a specified symbol, module, contract, or…

Skill by korefs

IndexedMIT

Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/korefs-blast-radius

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Determine what code, behavior, consumers, tests, schemas, services, and integrations could be affected by changing a specified symbol, module, contract, or behavior. Use before risky changes or when the user asks what could break. Read-only.

Use cases: documents

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/blast-radius

What's inside

Skill name: blast-radius
Description: Determine what code, behavior, consumers, tests, schemas, services, and integrations could be affected by changing a specified symbol, module, contract, or behavior. Use before risky changes or when the user asks what could break. Read-only.
License: MIT
Instructions: 60 lines in SKILL.md · view on GitHub

Files (1)

SKILL.md

SKILL.md (first lines)

# Blast Radius

Estimate the concrete impact surface of a proposed change using repository evidence.

## Workflow

1. Identify the exact target: symbol, file, API, schema, configuration, behavior, or component.
2. Find direct references and consumers.
3. Trace important indirect consumers through interfaces, dependency injection, events, routes, exports, shared models, and data contracts.
4. Identify tests that exercise the target or its consumers.
5. Inspect external boundaries such as:
   - APIs;
   - database schema/data;
   - queues/events;
   - caches;
   - configuration/environment variables;
   - serialization contracts;
   - filesystem/network protocols;
   - UI contracts.
6. Categorize impact by confidence.

## Confidence categories

- `Direct`: explicit reference or contract dependency.
- `Indirect`: verified downstream path through another component.
- `Potential`: plausible runtime/framework dependency that cannot be proven statically.

## Output

```text
## Target
...

## Direct consumers
- ...

## Indirect consumers
- ...

## External contracts
- ...

## Tests affected
- ...

## Potential hidden coupling
- ...

## Safest change strategy
- ...
```

Omit empty sections.

## Rules

- Do not exaggerate speculative impact.
- Do not modify code.
- Do not claim a consumer is affected solely because it has a similar name.

From korefs/skills, MIT.

Signals

Stars: 0
Forks: 0
Open issues: 0
Last commit (this folder): Sep 19, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/korefs/skills
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from korefs

Cite this page

blast-radius skill. Agent Mart. https://agentmart.dev/skills/korefs-blast-radius (last updated 2026-10-24)