light-review-existing-diffs

light-review-existing-diffs is a skill for Claude Code from blockmatic/basilic. It costs 43 tokens per session (223 once invoked), scanned A, original, MIT.

A quick review workflow for the changes currently shown in a project's diffs, meaning the code that differs from another version.

In plain words
What is it for?
Use it to inspect current code changes, identify risks, and record follow-up work.
Why use it?
It provides an early check for risky areas and unfinished polish before a deeper review.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to inspect current code changes, identify risks, and record follow-up work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/blockmatic/basilic/light-review-existing-diffs
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 blockmatic/basilic --skill light-review-existing-diffs
Clone the repo
git clone --depth 1 https://github.com/blockmatic/basilic

Made for: Claude Code.

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 light-review-existing-diffs

README.md
[![agentmods](https://agentmods.dev/badge/skills/blockmatic/basilic/light-review-existing-diffs.svg)](https://agentmods.dev/skills/blockmatic/basilic/light-review-existing-diffs)
Your own site
<a href="https://agentmods.dev/skills/blockmatic/basilic/light-review-existing-diffs"><img src="https://agentmods.dev/badge/skills/blockmatic/basilic/light-review-existing-diffs.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 223 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00043 $0.00223
Opus 5 $0.00022 $0.00112
Sonnet 5 $0.00009 $0.00045
Haiku 4.5 $0.00004 $0.00022

Measured 2d ago against content hash 883d388cc225, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

light-review-existing-diffs 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 2d 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.

.agents/skills/workflow/light-review-existing-diffs/SKILL.md · 20 lines

What it actually says

Purpose

Perform quick quality pass on current diffs to surface risky areas, ensure polish, and flag follow-up actions for deeper review.

Steps

  1. Scan recent changes: List open branches or pending commits requiring review, skim side-by-side diffs focusing on new/modified files, note files/modules with large/complex edits
  2. Assess quality signals: Watch for TODOs/debug code/commented blocks needing cleanup, verify naming/formatting/imports follow project standards, check that tests/documentation were updated when behavior changed
  3. Flag next actions: Mark sections warranting full review, capture questions for the author, and list quick fixes. Apply edits only if the user asked for them.

Completion

Read completion evidence before reporting completion.

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. 2d ago Changed · +7 lines 883d388cc225
  2. 4d ago First seen · 13 lines · 43 tokens per session scan A 9880be3f1cdc

Subscribe to this mod's changes

light-review-existing-diffs is a skill published in the GitHub repository blockmatic/basilic (89 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 223 once invoked, about $0.0002 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 2026-09-03.