agentmods.dev

review-ai

review-ai is a skill for Claude Code from pitimon/8-habit-ai-dev. It costs 41 tokens per session (2,897 once invoked), scanned A, original, MIT.

A review assistant for checking AI-generated code for security, quality, completeness, and performance after implementation.

In plain words
What is it for?
It is for reviewing code changes and tests, including checks for hardcoded secrets, injection, missing validation, cross-site scripting, oversized functions or files, weak error handling, and inefficient database access.
Why use it?
It helps catch unsafe code, missing tests, poor structure, and common performance problems before a change is committed.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the 8-habit-ai-dev plugin — 24 skills, 2 agents, 1 hook shipped together

not rated 3repo 1mo ago A scan 41 tokens original MIT

Good fit It is for reviewing code changes and tests, including checks for hardcoded secrets, injection, missing validation, cross-site scripting, oversized functions or files, weak error handling, and inefficient database access.

Compare 6 skills from other repositories ↓
View source ↗ pitimon/8-habit-ai-dev
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add pitimon/8-habit-ai-dev
Claude Code
/plugin install 8-habit-ai-dev

Made for: Claude Code.

Or install 8-habit-ai-dev, the plugin that ships this one along with the rest of its 24 skills, 2 agents, 1 hook.

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 review-ai

README.md
[![agentmods](https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/review-ai/github.svg)](https://agentmods.dev/skills/pitimon/8-habit-ai-dev/review-ai)
Your own site
<a href="https://agentmods.dev/skills/pitimon/8-habit-ai-dev/review-ai"><img src="https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/review-ai/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 review-ai

Your own site · 80×15
<a href="https://agentmods.dev/skills/pitimon/8-habit-ai-dev/review-ai"><img src="https://agentmods.dev/badge/skills/pitimon/8-habit-ai-dev/review-ai.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,897 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 $0.00041 $0.02897
Opus 5 $0.00020 $0.01448
Sonnet 5 $0.00008 $0.00579
Haiku 4.5 $0.00004 $0.00290

Measured 10d ago against content hash 70065888f767, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

review-ai 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 10d 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.

plugin/skills/review-ai/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Step 5: Review (อย่าไว้ใจทาง อย่าวางใจ AI)

Habit: H4 — Think Win-Win | Anti-pattern: Shipping AI-generated code without reading it

Process

  1. Get the diff: git diff --name-only HEAD to see what changed.

  2. Read the tests first — before judging the implementation, open the new or changed test files. Tests declare the intended behavior; reading them first gives you the specification to review the code against. If new logic has no corresponding test, record that as a Completeness finding in step 6.

  3. Security check (CRITICAL — block if found):

    • Hardcoded secrets (API keys, passwords, tokens)
    • SQL injection (string interpolation in queries)
    • Missing input validation on new endpoints
    • XSS vulnerabilities (unsanitized HTML output)

  4. Quality check (HIGH):

    • Functions >50 lines → break down
    • Files >800 lines → extract
    • Nesting >4 levels → simplify
    • Missing error handling on external calls
    • console.log or print() in production code

  5. Performance check (HIGH):

    • N+1 queries, unbounded loops, or sync blocking in hot paths
    • Missing pagination on list endpoints
    • Unindexed queries on large tables
    • Memory leaks (unclosed streams, unbounded caches, retained references)

    Performance findings follow the same evidence standard as the other axes: cite file:line with the measured or obvious-on-inspection cost.

  6. Completeness check (MEDIUM):

    • Edge cases handled (null, empty, malformed input)
    • Tests written for new functions (cross-check with step 2)
    • Docs updated if API changed

  7. AI-work budget and health check (MEDIUM, guidance only):

    • Did the work enter repeated loops, retries, or re-generation without new evidence?
    • Was context compacted or summarized, and was any summary verified against source files?
    • Is there enough audit evidence to explain what changed and why?
    • Does token, cost, or elapsed time look disproportionate to the task value?
    • Can the next session recover state from committed docs, issues, PRs, or handoff notes?
    • Does this PR add review burden, validator brittleness, generated-content noise, or contract drift?

Read the full file on GitHub · 219 lines

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. 10d ago First seen · 219 lines · 41 tokens per session scan A 70065888f767

Subscribe to this mod's changes

review-ai is a skill published in the GitHub repository pitimon/8-habit-ai-dev (3 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 2,897 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 2026-08-31.

Claude CodeCode reviewSecurityai-developmentanti-vibe-codingclaude-code-plugindeveloper-tools
Related

Other skills, from other repositories

two-axis-review

Two-axis review: Standards vs Spec, unmerged.

martineserios/thebrana · 15 tokens

code-review

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use…

martineserios/thebrana · 94 tokens

crap-analyzer

Use to produce a risk-based refactor + test plan for recently-changed code on a diff/branch/PR by computing CRAP (complexity × untested) on changed methods. Multi-language — TypeScript, JavaScript, Python, Java, Kotlin, Go, Ruby, C#, Rust, PHP — auto-discovers how the repo generates coverage. Triggers …

swingerman/engineer · 109 tokens

github-commenting

How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.

juspay/neurolink · 41 tokens

procoder

Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…

azrtydxb/procoder · 101 tokens

code-review

The depth half of a review - the dimensions a diff is read against (correctness, boundaries, concurrency, failure paths, secrets, data access, structure, test quality) and the rule that a finding is refuted before it is reported. The verdict stays with the reviewer agent. Use when reviewing a diff or a pull request…

jjanczur/tyran · 80 tokens