Skip to content
Back to skills

Changes

ASecurity

What the current diff touches and who reaches it — run before a commit or a PR

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 11, 2026
ai-agents

Works with

  • mcp

Security analysis

A100/100

Scanned November 11, 2026

npx -y skills add devmaxxx/zerograph --skill changes --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Changes?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Changes
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/devmaxxx-changes/badge)](https://www.skillsdirectory.com/skills/devmaxxx-changes)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
description: What the current diff touches and who reaches it — run before a commit or a PR
argument-hint: "[base] [--depth N]"
allowed-tools: mcp__plugin_zerograph_zerograph__changes
disable-model-invocation: true
---

Call `mcp__plugin_zerograph_zerograph__changes` for: $ARGUMENTS

A first word that is not a flag is `base`, the revision to diff against (`main` reads the whole
branch); none leaves it at the uncommitted diff. `--depth N` sets `depth` (1 is the direct callers
alone; the default is 2). The answer is a risk word, the symbols the diff touches and the callers
that reach them.

1. Lead with the risk word and the touched symbols.
2. For each affected caller outside the diff, open its `path:line` and say whether the change can
   break it: a new parameter, a changed return, a renamed export. Those are the review's and the
   test plan's real targets.
3. Name the affected callers no test covers, if any stand out. A caller list is the graph's view; a
   dynamic call has no edge, so Grep the changed names before calling a change contained.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.