agentmods.dev

code-review-light

code-review-light is a skill for Claude Code from d-mariano/spicyclaude. It costs 68 tokens per session (629 once invoked), scanned A, original, MIT.

A read-only tool for reviewing the code changed in a pull request or branch. It checks the diff once and groups findings by severity.

In plain words
What is it for?
Use it to inspect changed code for behavior mistakes, exploitable security problems, unnecessary complexity, and outdated comments or documentation.
Why use it?
It provides a quick review without changing the code, posting comments, approving the pull request, or merging it.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter; mentions CLAUDE.md; mentions subagents.

not rated 5repo 1mo ago A scan 68 tokens original MIT

Good fit Use it to inspect changed code for behavior mistakes, exploitable security problems, unnecessary complexity, and outdated comments or documentation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/d-mariano/spicyclaude/code-review-light
View source ↗ d-mariano/spicyclaude
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 d-mariano/spicyclaude --skill code-review-light
Clone the repo
git clone --depth 1 https://github.com/d-mariano/spicyclaude

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 code-review-light

README.md
[![agentmods](https://agentmods.dev/badge/skills/d-mariano/spicyclaude/code-review-light/github.svg)](https://agentmods.dev/skills/d-mariano/spicyclaude/code-review-light)
Your own site
<a href="https://agentmods.dev/skills/d-mariano/spicyclaude/code-review-light"><img src="https://agentmods.dev/badge/skills/d-mariano/spicyclaude/code-review-light/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.

agentmods 80×15 button for code-review-light

Your own site · 80×15
<a href="https://agentmods.dev/skills/d-mariano/spicyclaude/code-review-light"><img src="https://agentmods.dev/badge/skills/d-mariano/spicyclaude/code-review-light.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 629 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 $0.00068 $0.00629
Opus 5 $0.00034 $0.00315
Sonnet 5 $0.00014 $0.00126
Haiku 4.5 $0.00007 $0.00063

Measured 9d ago against content hash dc7dbed5dec0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

code-review-light 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 9d 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.

skills/code-review-light/SKILL.md · 43 lines

What it actually says

Light Code Review (single pass)

A quick, read-only, single-pass review. No fan-out, no subagents. Pull the diff, review it once against the shared standard, print a tiered summary. Never post, approve, or merge.

Argument ($ARGUMENTS): a PR number, a branch name, or a set of files. If empty, review the current branch against its base.

Steps

  1. Get the diff.

    • PR number → gh pr diff <n> (and gh pr view <n> --json title,body for intent).
    • Branch → git diff <base>...HEAD (base is main/master unless the repo says otherwise).
    • Files → restrict to those paths in the current diff. Review only the changed code.

  2. One consolidated pass. In a single read, look for: behavior that doesn't match the PR's stated intent, concretely exploitable security flaws, unnecessary complexity / over-engineering, and comment/doc rot. Apply the shared standard — do not restate it here:

  3. Filter. Every finding needs severity + confidence 0–100 + file:line + concrete fix. Drop anything below confidence 80. Drop anything on the what-not-to-flag list.

  4. Print a severity-tiered summary (Critical → High → Medium → Low), each line in the rubric's rendering format (- [NN] path:line — **Title.** problem. Fix: …). End with a one-line takeaway. If nothing survives the gate, say No concerns identified.

Scope note: this runs in a forked Explore context, which does not load CLAUDE.md. For CLAUDE.md / guideline-violation checks, full coverage, or posting to a PR, use /review-heavy. This skill is also the Low risk tier fast path in risk-tiering.md.

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. 9d ago First seen · 43 lines · 68 tokens per session scan A dc7dbed5dec0

Subscribe to this mod's changes

code-review-light is a skill published in the GitHub repository d-mariano/spicyclaude (5 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 629 once invoked, about $0.0003 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 2026-08-31.

Code review
Related

Other skills, from other repositories

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

rework-rate

Measure and interpret PR rework rate — the emerging 5th DORA metric.

bradygaster/squad · 20 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

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"…

umputun/revdiff · 84 tokens

code-reviewer

Code review specialist focused on patterns, bugs, security, and performance.

RightNow-AI/openfang · 17 tokens

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…

LeoYeAI/openclaw-master-skills · 115 tokens