sc-diff-report

sc-diff-report is a skill for Claude Code from fatihkan/badi. It costs 21 tokens per session (2,007 once invoked), scanned A, a copy of sc-diff-report, MIT.

A security scan for only the files changed in a Git diff, pull request, or recent commit. It separates security issues introduced by the change from issues that were already present.

In plain words
What is it for?
Use it to scan pull requests, staged changes, commits, or a chosen Git revision range and produce a change-focused security report.
Why use it?
It provides focused feedback for code review without scanning the entire codebase each time. This helps teams concentrate on new risks in a change.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Part of the badi plugin — 81 skills, 86 commands, 30 agents, 7 hooks shipped together

Good fit Use it to scan pull requests, staged changes, commits, or a chosen Git revision range and produce a change-focused security report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fatihkan/badi/sc-diff-report
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add fatihkan/badi --skill sc-diff-report
Clone the repo
git clone --depth 1 https://github.com/fatihkan/badi

Made for: Claude Code.

Or install badi, the plugin that ships this one along with the rest of its 81 skills, 86 commands, 30 agents, 7 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 sc-diff-report

README.md
[![agentmods](https://agentmods.dev/badge/skills/fatihkan/badi/sc-diff-report.svg)](https://agentmods.dev/skills/fatihkan/badi/sc-diff-report)
Your own site
<a href="https://agentmods.dev/skills/fatihkan/badi/sc-diff-report"><img src="https://agentmods.dev/badge/skills/fatihkan/badi/sc-diff-report.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,007 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 98% copy Near-identical to another mod 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 $0.00021 $0.02007
Opus 5 $0.00010 $0.01004
Sonnet 5 $0.00004 $0.00401
Haiku 4.5 $0.00002 $0.00201

Measured yesterday against content hash 069eb7d36a7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sc-diff-report 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 yesterday.

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.

Origin

This is a copy

98% identical to sc-diff-report — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills-vault/security-check/sc-diff-report/SKILL.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SC: Diff Report — Incremental Security Scan

Purpose

Performs a targeted security scan on only the files changed in a git diff, pull request, or recent commit. This enables fast, focused security feedback during code review without the overhead of a full codebase scan. Classifies findings as "new" (introduced by changes) vs "existing" (pre-existing in touched files).

Activation

Activates when the user issues any of:

  • "scan diff"
  • "scan changes"
  • "PR scan"
  • "scan commit"
  • "incremental scan"

Output

File: security-report/diff-report.md

Phase 1: Change Detection

Git Diff Extraction

Determine the diff scope based on user context:

PR Mode (most common):

git diff main...HEAD --name-only
git diff main...HEAD

Staged changes:

git diff --cached --name-only
git diff --cached

Last commit:

git diff HEAD~1 --name-only
git diff HEAD~1

Custom range:

git diff {base}...{head} --name-only
git diff {base}...{head}

Changed File Inventory

From the diff output, build an inventory:

  1. Added files — entirely new files (highest priority)
  2. Modified files — existing files with changes
  3. Deleted files — removed files (check for orphaned references)
  4. Renamed files — detect renames with content changes

For each changed file, record:

  • File path
  • Change type (added/modified/deleted/renamed)
  • Lines added (line numbers)
  • Lines removed (line numbers)
  • Total change size (lines added + removed)

Change Filtering

Filter out changes unlikely to have security impact:

  • Documentation files (.md, .txt, .rst) — skip unless they contain config
  • Test files — scan but mark as test context
  • Generated files — skip (check for generated markers)
  • Lock files — delegate to sc-dependency-audit pattern matching
  • Static assets (images, fonts, CSS) — skip
  • Configuration files — keep, high priority for security review

Dependency Change Detection

If lock files or manifests changed:

  • package.json / package-lock.json — extract added/removed/updated packages
  • go.mod / go.sum — extract module changes
  • Cargo.toml / Cargo.lock — extract crate changes
  • requirements.txt / poetry.lock — extract package changes
  • Flag newly added dependencies for supply chain review

Read the full file on GitHub · 247 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. yesterday First seen · 247 lines · 21 tokens per session scan A 069eb7d36a7a

Subscribe to this mod's changes

sc-diff-report is a skill published in the GitHub repository fatihkan/badi (7 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 2,007 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to sc-diff-report, differing in 1 line, and is treated as a copy.