Borrowing it
Nothing to install: this file belongs to P4ST4S/mcp-audit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/P4ST4S/mcp-audit/main/.agents/skills/differential-review/SKILL.mdgit clone --depth 1 https://github.com/P4ST4S/mcp-auditWrote 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/p4st4s/mcp-audit/differential-review)<a href="https://agentmods.dev/skills/p4st4s/mcp-audit/differential-review"><img src="https://agentmods.dev/badge/skills/p4st4s/mcp-audit/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/p4st4s/mcp-audit/differential-review"><img src="https://agentmods.dev/badge/skills/p4st4s/mcp-audit/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 | $0.00097 | $0.01738 |
| Opus 5.5 | $0.00039 | $0.00695 |
| Sonnet 5.5 | $0.00019 | $0.00348 |
| Haiku 4.5 | $0.00010 | $0.00174 |
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.
This is a copy
83% identical to differential-review — 22 lines 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.
How it starts
The opening of the file, as written. The whole thing — 226 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
- Risk-First: Focus on auth, crypto, value transfer, external calls
- Evidence-Based: Every finding backed by git history, line numbers, attack scenarios
- Adaptive: Scale to codebase size (SMALL/MEDIUM/LARGE)
- Honest: Explicitly state coverage limits and confidence level
- 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
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 226 lines · 97 tokens per session scan A f9af6a8193fc
differential-review is a skill published in the GitHub repository P4ST4S/mcp-audit (8 stars, last pushed 4d ago), licensed Apache-2.0. It adds 97 tokens to every session and 1,738 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 83% identical to differential-review, differing in 22 lines, and is treated as a copy.
Other skills, from other repositories
bmad-loop-resolve
Interactive escalation-resolution workflow for the bmad-loop orchestrator. A bmad-loop run paused on a CRITICAL escalation (a contradiction or gap a dev/review session could not safely resolve alone); you and the human disambiguate the frozen spec so the story can be re-driven. Invoked as /bmad-loop-resolve . Unlike…
bmad-review-edge-case-hunter
Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.
bmad-loop
Iterate over a list of story keys, executing dev → review → PR → CI → merge for each. Use when the user says "loop these stories [list]" or "run the loop on [story keys]".
bmad-retrospective
Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]".
bmad-editorial-review-structure
Structural editor that proposes cuts, reorganization, and simplification while preserving comprehension. Use when user requests structural review or editorial review of structure.
bmad-code-review
Review code changes adversarially using parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with structured triage into actionable categories. Use when the user says "run code review" or "review this code".