Borrowing it
Nothing to install: this file belongs to mtarcure/claude-vibe-squad. 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/mtarcure/claude-vibe-squad/main/.agents/skills/differential-review/SKILL.mdgit clone --depth 1 https://github.com/mtarcure/claude-vibe-squadWrote 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/mtarcure/claude-vibe-squad/differential-review)<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/differential-review"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/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/mtarcure/claude-vibe-squad/differential-review"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/differential-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00080 | $0.00421 |
| Opus 5 | $0.00040 | $0.00211 |
| Sonnet 5 | $0.00016 | $0.00084 |
| Haiku 4.5 | $0.00008 | $0.00042 |
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 11d 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.
What it actually says
Differential Review
Review a change by comparing behavior before and after, rather than by reading the new code in isolation.
Steps
- Build the two states: base and head. Anything that cannot be built in both states cannot be differentially reviewed — say so instead of guessing.
- Enumerate observable surfaces the change could move: return values, persisted rows, emitted events, logs, exit codes, wire formats, timing, and error text.
- For each surface, predict the intended delta from the change's stated intent, then measure the actual delta.
- Treat every unpredicted delta as a finding until explained. Silent behavior changes are the class this method exists to catch.
- Pay special attention to the unchanged-looking paths: refactors that preserve the happy path frequently move error, empty, and boundary behavior.
- Where a surface cannot be measured, construct the smallest differential test that would measure it, and note the gap if the test is out of scope.
- Compare against a scalar or previous reference implementation where one exists — vectorized, cached, or rewritten code is unverified without it.
- Record deltas that are intended-but-breaking separately from deltas that are unintended; they need different decisions from the operator.
Acceptance
- Base and head were both built or run; if not, the review states that it is analysis-only.
- Every moved surface is listed with predicted versus observed behavior.
- Unpredicted deltas are reported as findings or explicitly explained.
- Error, empty, and boundary paths are covered, not just the happy path.
- Intended-breaking and unintended changes are distinguished.
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.
- 11d ago First seen · 27 lines · 80 tokens per session scan A 55884a04684c
differential-review is a skill published in the GitHub repository mtarcure/claude-vibe-squad (148 stars, last pushed 2d ago), licensed MIT. It adds 80 tokens to every session and 421 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 2026-08-30.
Other skills, from other repositories
cw-slice
Use before writing code for any Codewhale feature, upgrade, or refactor: find the existing owner of the behavior, bound the change to one reviewable slice, and fix the evidence bar before you start.
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
gh-compile-issues
Triage N GitHub issues into a coverage matrix: fetch each, check current code, classify already-done/quick-fix/design/defer with cited evidence.
review
Read-only correctness review with actionable findings first, tight file/line evidence, severity, and a concise residual-risk summary.
simplify
Improve clarity and reduce needless complexity after behavior is understood; preserve behavior and keep cleanup separate from correctness fixes.
review-team
Use when assigned a review or when an authored review boundary is reached.