Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/woohyun212/security-skill/differential-review)<a href="https://agentmods.dev/skills/woohyun212/security-skill/differential-review"><img src="https://agentmods.dev/badge/skills/woohyun212/security-skill/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.
<a href="https://agentmods.dev/skills/woohyun212/security-skill/differential-review"><img src="https://agentmods.dev/badge/skills/woohyun212/security-skill/differential-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.02605 |
| Opus 5 | $0.00012 | $0.01303 |
| Sonnet 5 | $0.00005 | $0.00521 |
| Haiku 4.5 | $0.00002 | $0.00261 |
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 10d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
os.system(user_input) How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What this skill does
Analyzes git diffs, pull request changes, and commit ranges for security regressions. Unlike a full codebase audit, this skill focuses exclusively on what changed: additions that introduce new vulnerabilities (hardcoded secrets, injection sinks, unsafe deserialization), and removals that eliminate security controls (auth checks, input validation, rate limiting). It classifies changed files by risk tier, runs targeted pattern checks on additions and deletions, cross-references dependency changes, and produces a prioritized findings list with severity.
When to use
- During pull request review when you need a security-focused lens on the diff specifically
- When a commit range is suspected of introducing a regression (e.g., after an incident or pentest finding)
- As a lightweight pre-merge gate before running a full
secure-code-review - When reviewing dependency bumps that may silently alter security behavior
- When a developer says "I only changed X" and you need to verify that claim from a security perspective
Prerequisites
- Git access to the repository (local clone or remote diff URL)
gitCLI available in the environment- (Optional)
semgrepfor automated pattern matching on additions - Read access to dependency manifests (
package.json,go.mod,requirements.txt,Cargo.toml, etc.)
Inputs
| Item | Description | Example |
|---|---|---|
DIFF_SOURCE |
Source of the diff to review | git diff main..feature/login, PR URL, patch file |
BASE_REF |
Base branch or commit | main, v2.3.1, abc1234 |
HEAD_REF |
Target branch or commit | feature/auth-refactor, HEAD, def5678 |
REPO_PATH |
Path to the local repository | /home/user/myapp |
LANGUAGE |
Primary language(s) in the diff | Python, TypeScript, Go |
Workflow
Step 1: Obtain the diff
Choose the appropriate method based on DIFF_SOURCE:
# Commit range
git diff <BASE_REF>..<HEAD_REF>
# Staged changes only
git diff --cached
# Specific files in a range
git diff <BASE_REF>..<HEAD_REF> -- path/to/file
# Full diff with context (recommended for security review)
git diff -U5 <BASE_REF>..<HEAD_REF>
# List only changed files for triage
git diff --name-only <BASE_REF>..<HEAD_REF>
# Include commit messages for context
git log --oneline <BASE_REF>..<HEAD_REF>
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.
- 10d ago First seen · 269 lines · 24 tokens per session scan A 36ea33bec261
differential-review is a skill published in the GitHub repository woohyun212/security-skill (21 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 2,605 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…