differential-review

differential-review is a skill for Claude Code from RedHatProductSecurity/prodsec-skills. It costs 61 tokens per session (12,089 once invoked), scanned A, original, Apache-2.0.

A security-focused review of code changes such as pull requests, commits, or diffs. It uses the surrounding code and its Git history to assess risks, affected components, tests, and possible security regressions.

In plain words
What is it for?
Reviewing changes involving authentication, cryptography, money transfers, external calls, dependent code paths, and missing or insufficient tests, with results saved as a Markdown report.
Why use it?
It helps reviewers spot dangerous changes that may look small or like harmless refactoring, and records findings with evidence instead of relying on memory or a verbal review.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the prodsec-skills plugin — 133 skills shipped together

Good fit Reviewing changes involving authentication, cryptography, money transfers, external calls, dependent code paths, and missing or insufficient tests, with results saved as a Markdown report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redhatproductsecurity/prodsec-skills/differential-review
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 RedHatProductSecurity/prodsec-skills --skill differential-review
Clone the repo
git clone --depth 1 https://github.com/RedHatProductSecurity/prodsec-skills

Made for: Claude Code.

Or install prodsec-skills, the plugin that ships this one along with the rest of its 133 skills.

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 differential-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/redhatproductsecurity/prodsec-skills/differential-review/github.svg)](https://agentmods.dev/skills/redhatproductsecurity/prodsec-skills/differential-review)
Your own site
<a href="https://agentmods.dev/skills/redhatproductsecurity/prodsec-skills/differential-review"><img src="https://agentmods.dev/badge/skills/redhatproductsecurity/prodsec-skills/differential-review/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 differential-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/redhatproductsecurity/prodsec-skills/differential-review"><img src="https://agentmods.dev/badge/skills/redhatproductsecurity/prodsec-skills/differential-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,089 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Prompt Injection · line 14
    Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
    Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
  • medium Excessive Agency · line 1610
    Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.
    Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
  • medium Excessive Agency · line 1614
    Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.
    Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
How audits are shown
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 $0.00061 $0.12089
Opus 5 $0.00030 $0.06045
Sonnet 5 $0.00012 $0.02418
Haiku 4.5 $0.00006 $0.01209

Measured 12d ago against content hash 6d21b2002557, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

differential-review scanned grade A with 1 finding 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

git diff <range> | grep "^+" | grep -E "requests\.|httpx\.|urllib|aiohttp|http\.Get|http\.Post|http\.NewRequest|net\.Dial"
module/skills/differential-review/SKILL.md · 1,766 lines

How it starts

The opening of the file, as written. The whole thing — 1,766 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Differential Security Review

Security-focused code review for PRs, commits, and diffs.

Core Principles

  1. Risk-First: Focus on auth, crypto, value transfer, external calls
  2. Evidence-Based: Every finding backed by git history, line numbers, attack scenarios
  3. Adaptive: Scale to codebase size (SMALL/MEDIUM/LARGE)
  4. Honest: Explicitly state coverage limits and confidence level
  5. Output-Driven: Always generate comprehensive markdown report file

Rationalizations (Do Not Skip)

Rationalization Why It's Wrong Required Action
"Small PR, quick review" Heartbleed was 2 lines Classify by RISK, not size
"I know this codebase" Familiarity breeds blind spots Build explicit baseline context
"Git history takes too long" History reveals regressions Never skip Phase 1
"Blast radius is obvious" You'll miss transitive callers Calculate quantitatively
"No tests = not my problem" Missing tests = elevated risk rating Flag in report, elevate severity
"Just a refactor, no security impact" Refactors break invariants Analyze as HIGH until proven LOW
"I'll explain verbally" No artifact = findings lost Always write report

Quick Reference

Codebase Size Strategy

Codebase Size Strategy Approach
SMALL (<20 files) DEEP Read all deps, full git blame
MEDIUM (20-200) FOCUSED 1-hop deps, priority files
LARGE (200+) SURGICAL Critical paths only

Risk Level Triggers

Risk Level Triggers
HIGH Auth, crypto, external calls, value transfer, validation removal
MEDIUM Business logic, state changes, new public APIs
LOW Comments, tests, UI, logging

Workflow Overview

Pre-Analysis → Phase 0: Triage → Phase 1: Code Analysis → Phase 2: Test Coverage
    ↓              ↓                    ↓                        ↓
Phase 3: Blast Radius → Phase 4: Deep Context → Phase 5: Adversarial → Phase 6: Report

Read the full file on GitHub · 1,766 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. 12d ago First seen · 1,766 lines · 61 tokens per session scan A 6d21b2002557

Subscribe to this mod's changes

differential-review is a skill published in the GitHub repository RedHatProductSecurity/prodsec-skills (52 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 61 tokens to every session and 12,089 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.