diff-impact

diff-impact is a command for Claude Code from felvieira/claude-skills-fv. It costs 119 tokens per session (1,233 once invoked), scanned A, original, Apache-2.0.

A change-impact command that examines a Git diff and a code dependency graph. A dependency graph maps which parts of a codebase rely on other parts.

In plain words
What is it for?
Use it before opening a pull request, during final review, after a refactor, or when changing an old complex module. It reports directly changed code and dependents up to a chosen number of steps away.
Why use it?
It shows whether an uncommitted change or branch affects only one area or may break dependent code elsewhere. This helps developers review wider consequences before merging.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is Bash(node scripts/diff-impact.mjs *), Read, Grep.

Part of the dev-team-kit-fv plugin — 72 skills, 45 commands, 16 agents, 5 hooks shipped together

Good fit Use it before opening a pull request, during final review, after a refactor, or when changing an old complex module. It reports directly changed code and dependents up to a chosen number of steps away.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/felvieira/claude-skills-fv
agentmods
npx agentmods add commands/felvieira/claude-skills-fv/diff-impact

Made for: Claude Code.

Or install dev-team-kit-fv, the plugin that ships this one along with the rest of its 72 skills, 45 commands, 16 agents, 5 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for diff-impact

README.md
[![agentmods](https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/diff-impact/github.svg)](https://agentmods.dev/commands/felvieira/claude-skills-fv/diff-impact)
Your own site
<a href="https://agentmods.dev/commands/felvieira/claude-skills-fv/diff-impact"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/diff-impact/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for diff-impact

Your own site · 80×15
<a href="https://agentmods.dev/commands/felvieira/claude-skills-fv/diff-impact"><img src="https://agentmods.dev/badge/commands/felvieira/claude-skills-fv/diff-impact.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 119 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,233 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00119 $0.01233
Opus 5 $0.00060 $0.00616
Sonnet 5 $0.00024 $0.00247
Haiku 4.5 $0.00012 $0.00123

Measured 11d ago against content hash 2235bb4cd155, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

diff-impact scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/diff-impact.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/diff-impact — Ripple analysis antes do merge

Cruza git diff com graphify-out/graph.json pra responder: se eu mergear isso agora, o que mais pode quebrar?

Inspirado em /understand-diff do Lum1104/Understand-Anything (MIT). Implementação própria — zero-dep Node, usa o graphify-out/ já existente.

Quando usar

  • Antes de abrir PR — saber se a mudança é local ou cross-cutting
  • Durante review final (skill 11) — confirmar que o reviewer olhou todos os pontos afetados
  • Após refactor — validar que ripple ficou contido
  • Em legacy — antes de tocar um módulo godzilla, ver quem mais depende dele

Quando NÃO usar

  • Repo sem graphify-out/graph.json (rode graphify update . antes)
  • Mudança em arquivo não-código (markdown, JSON, configs) — graphify só indexa código
  • Hot-fix urgente que não pode esperar análise

Modos

# vs HEAD~1 (último commit)
node scripts/diff-impact.mjs

# vs staged (antes de commit)
node scripts/diff-impact.mjs --staged

# vs branch main
node scripts/diff-impact.mjs --ref main

# ajustar profundidade BFS (default 2)
node scripts/diff-impact.mjs --depth 3

# machine-readable
node scripts/diff-impact.mjs --json

Output esperado

Diff Impact Analysis
========================================================================
Changed files: 3 (matched 3 in graph, unmatched 0)
Directly touched nodes: 7
Dependents in 2 hops (the ripple): 18
Dependencies in 2 hops (what changed code calls): 12

Directly touched:
  validateInput()                          src/lib/validators.ts
  parseAuth()                              src/lib/auth.ts
  ...

Ripple — who depends on the touched code (depth 2):
  hop 1: 11 nodes
    - loginHandler                          src/routes/login.ts
    - signupHandler                         src/routes/signup.ts
    ...
  hop 2: 7 nodes
    - resetPasswordRoute                    src/routes/password.ts
    ...

Risk Banding

A partir de dependents_count (ripple), 3 faixas qualitativas — ponto de partida a calibrar por projeto, não constantes universais:

Read the full file on GitHub · 118 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 118 lines · 119 tokens per session scan A 2235bb4cd155

Subscribe to this mod's changes

diff-impact is a command published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 119 tokens to every session and 1,233 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.