differential-review

differential-review is a skill for Claude Code, Codex from NOMARJ/sigil. It costs 72 tokens per session (1,037 once invoked), scanned A, original, Apache-2.0.

A security-focused review of Git changes that examines a diff together with the surrounding code and system behavior.

In plain words
What is it for?
Use it when reviewing pull requests or preparing merges, especially for changes to authentication, personal data, payments, infrastructure, APIs, or data storage.
Why use it?
It helps detect attack-surface changes and security regressions that a line-by-line scan of only the edited code may miss.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when reviewing pull requests or preparing merges, especially for changes to authentication, personal data, payments, infrastructure, APIs, or data storage.

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

Made for: Claude Code, Codex.

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/nomarj/sigil/differential-review.svg)](https://agentmods.dev/skills/nomarj/sigil/differential-review)
Your own site
<a href="https://agentmods.dev/skills/nomarj/sigil/differential-review"><img src="https://agentmods.dev/badge/skills/nomarj/sigil/differential-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,037 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 $0.00072 $0.01037
Opus 5 $0.00036 $0.00518
Sonnet 5 $0.00014 $0.00207
Haiku 4.5 $0.00007 $0.00104

Measured 4d ago against content hash 7bc8616e371a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

differential-review 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 4d 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.

packs/security/skills/owasp-security/differential-review/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Differential Security Review

Adapted from Trail of Bits' differential-review skill. Layer 2 analysis — runs on PRs and merges, examining not just what changed but what the change means in context.

How This Differs from Layer 1

Layer 1 scans look at code in isolation — "is this line dangerous?" Layer 2 looks at the change in context — "does this change create a new attack surface, alter the security model, or introduce a vulnerability path that didn't exist before?"

Review Methodology

1. Change Classification

Before diving into code, classify the change:

  • Security-critical: Touches auth, authz, crypto, PII, payment, or infrastructure
  • Security-adjacent: Touches input handling, API endpoints, data storage, or external integrations
  • Security-neutral: UI changes, documentation, refactoring with no behavioral change

This classification determines review depth. Security-critical changes get line-by-line analysis. Security-neutral changes get a quick scan for accidental security regressions.

2. Attack Surface Analysis

For every change, ask:

  • New endpoints? Every new route/endpoint is a new entry point for attackers
  • New data flows? Does data move to a new destination? Does sensitive data reach a new component?
  • Changed trust boundaries? Does this change what code is trusted vs. untrusted?
  • Changed permissions? Does this alter who can do what?
  • New dependencies? (Feeds into supply-chain audit)

3. Contextual Analysis

Read the diff in context of surrounding code:

  • Does the changed function handle user input upstream?
  • Are the changed values used in security-sensitive operations downstream?
  • Does this change alter assumptions that other code relies on?
  • Does the git history show this area has been fixed for security issues before? (Recurrence pattern)

4. Common Differential Vulnerabilities

Changes that look innocent but aren't:

  • Adding a new API field that exposes internal data
  • Changing a default value from deny to allow
  • Adding a code path that bypasses existing validation
  • Refactoring that removes a security check as "dead code"
  • Adding logging that captures sensitive data
  • Changing error handling from fail-closed to fail-open

Read the full file on GitHub · 103 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. 4d ago First seen · 103 lines · 72 tokens per session scan A 7bc8616e371a

Subscribe to this mod's changes

differential-review is a skill published in the GitHub repository NOMARJ/sigil (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,037 once invoked, about $0.0004 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 2026-09-04.