agentmods.dev

code-review-lite

code-review-lite is a skill for Claude Code from gsarig/skills. It costs 65 tokens per session (618 once invoked), scanned A, original, MIT.

A shortened code review for small or low-risk changes. It checks whether the code matches its obvious purpose, is readable, and follows nearby patterns.

In plain words
What is it for?
Use it for small code changes that are not security-sensitive. It can inspect a diff, run linting when appropriate, load JavaScript security guidance when needed, and check for common review problems.
Why use it?
It gives a focused review without the longer requirements work used for larger reviews. It can avoid repeating lint checks that continuous integration already performs for pull requests.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

not rated 30repo changed 22d ago A scan SkillSpector: pass 65 tokens original MIT

Good fit Use it for small code changes that are not security-sensitive. It can inspect a diff, run linting when appropriate, load JavaScript security guidance when needed, and check for common review problems.

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

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-lite

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/gsarig/skills/code-review-lite"><img src="https://agentmods.dev/badge/skills/gsarig/skills/code-review-lite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 618 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 $0.00065 $0.00618
Opus 5.5 $0.00026 $0.00247
Sonnet 5.5 $0.00013 $0.00124
Haiku 4.5 $0.00006 $0.00062

Measured 22d ago against content hash 9cf2e974a416, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-review-lite 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 22d 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-lite/SKILL.md · 47 lines

What it actually says

Steps

1. Source and diff

If --source and the corresponding identifier args were passed, the orchestrator already resolved the source: skip source detection and read only the diff-fetching and output-format sections of ~/.claude/skills/code-review/references/review-shared.md, then fetch the diff for that mode. Otherwise, read ~/.claude/skills/code-review/references/review-shared.md and follow its source detection and diff fetching sections.

2. Lint (conditional)

Skip the linter when source mode is pr and --lint was not passed (CI runs the linter on the PR).

Otherwise run the linter per the linter detection section of the shared doc.

3. Load language references (conditional)

If any changed path matches \.(js|jsx|ts|tsx|mjs|cjs)$, read ~/.claude/skills/code-review/references/js-security.md.

4. GitHub Actions hash verification (conditional)

If the diff contains any line matching ^\+\s*uses:\s+\S+@[0-9a-f]{40}, run the verification per the shared doc.

5. Review

Read ~/.claude/skills/code-review/references/review-checklist.md first for general principles.

Focus on:

  • Correctness against obvious intent. Lite reviews do not gather requirements; reason about what the diff is trying to do from the code itself.
  • Readability and naming.
  • Matches existing patterns in the file or nearby files.
  • Dead code, debug artefacts, accidental scope creep.
  • Security issues that are visible without deep analysis (hardcoded secrets, obvious injection, missing input validation on user-facing entry points).

Do not deep-dive architecture or push for refactors beyond the diff. Honour the common review rules in the shared doc.

6. Output

Format per the output section of ~/.claude/skills/code-review/references/review-shared.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. 22d ago Changed 9cf2e974a416
  2. 2mo ago First seen · 47 lines · 65 tokens per session scan A 97716bc42c42

Subscribe to this mod's changes

code-review-lite is a skill published in the GitHub repository gsarig/skills (30 stars, last pushed 13d ago), licensed MIT. It adds 65 tokens to every session and 618 once invoked, about $0.0003 per session on Opus 5.5. 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.

Code review
Related

code-review-lite compared with skills from other repositories

code-review-lite next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
code-review-litegsarig/skillsSkill3013d agoMITA65Claude Code
autoreviewopenclaw/clawhubSkill9.5kyesterdayMITA17Claude Code, Codex
agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skillsSkill2.2k6d agoMITA115Claude Code, Codex
omh-code-reviewrlaope/oh-my-hermesSkill5.2kyesterdayMITA48Claude Code, Codex
revdiff-planumputun/revdiffSkill945yesterdayMITA84Claude Code
explore-unknownsdzhng/skillsSkill1.4k2d agoMITA162Claude Code, Codex
re0-mergeLilMGenius/paperthinSkill1.4k4d agoMITA70Claude Code