code-review

code-review is a skill for Claude Code, Codex from husniadil/ekstend. It costs 39 tokens per session (7,755 once invoked), scanned A, original, MIT.

A guided code review process that examines either a change against a base branch or an entire codebase. It finds gaps, lets a person choose which findings to address, and repeats the review after fixes.

In plain words
What is it for?
Use it for pull-request reviews or audits of selected folders or a whole project. It can identify issues, apply selected fixes, and check the result again.
Why use it?
It turns a large or repeated review into manageable cycles with human decisions at each stage. It helps catch correctness, design, and broader code-quality problems before work is considered finished.

Skill for Claude CodeCodex

Part of the code-review plugin — 2 skills shipped together

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.

agentmods
npx agentmods add skills/husniadil/ekstend/code-review
Any agent
npx skills add husniadil/ekstend --skill code-review
Clone the repo
git clone --depth 1 https://github.com/husniadil/ekstend

Made for: Claude Code, Codex.

Or install code-review, the plugin that ships this one along with the rest of its 2 skills.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/husniadil/ekstend/code-review.svg)](https://agentmods.dev/skills/husniadil/ekstend/code-review)
Your own site
<a href="https://agentmods.dev/skills/husniadil/ekstend/code-review"><img src="https://agentmods.dev/badge/skills/husniadil/ekstend/code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,755 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00039 $0.07755
Opus 5 $0.00019 $0.03877
Sonnet 5 $0.00008 $0.01551
Haiku 4.5 $0.00004 $0.00775

Measured 4d ago against content hash 130dfcb897dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 4d 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.

plugins/code-review/skills/code-review/SKILL.md · 676 lines

How it starts

The opening of the file, as written. The whole thing — 676 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review - Iterative Review

An iterative, human-in-loop code review skill that identifies gaps, presents them for user selection, and fixes them in cycles until clean.

Review Modes

Two modes. Pick based on user intent — detail for each mode is covered in Step 0 below.

  • PR Review Mode (default): diff-based review against a base branch
  • Holistic Review Mode: audit an entire codebase or scoped directories

Subagent Mode (argument)

The skill accepts one optional argument via $ARGUMENTS controlling whether scans/fixes delegate to Task subagents:

$ARGUMENTS value Meaning
subagent Always delegate eligible work to subagents — Explore for read-only scans (Step 0 Holistic, Step 5 re-review), general-purpose for multi-file complex fixes (Step 4)
no-subagent Never call the Task tool. Do everything in the main context: Glob + Read + Grep directly, apply fixes directly
auto Let the skill decide based on scope size, codebase breadth, and fix complexity
(empty) Same as auto

Default: auto. If $ARGUMENTS is empty or not recognized, operate in auto mode.

auto decision heuristics:

  • Holistic scan over >50 files or multiple ecosystem packages → delegate to Explore subagent
  • Fix touches >2 files or needs cross-cutting refactor → delegate to general-purpose subagent
  • Small PR diff / single-file scope / known surface → stay in main context
  • Tight budget / urgency signal from user → stay in main context

Read the full file on GitHub · 676 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 676 lines · 39 tokens per session scan A 130dfcb897dc

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository husniadil/ekstend (1 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 7,755 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.

Related

Other skills, from other repositories

subagent-driven-development

Use when a written implementation plan exists and the user wants to execute it — "execute this plan", "implement the plan", "run the plan", "build it", "subagent-driven development". Plans + confirms in this session, then hands a lightweight task list to a deterministic background Workflow that runs per-task implement…

jasonm4130/claude-skills · 102 tokens

brainstorming

Use before feature or design work that carries real ambiguity or a load-bearing decision, ahead of writing implementation code — explores intent, requirements and design first. Do NOT use for trivial changes, mechanical edits, or work whose design is already settled.

jasonm4130/claude-skills · 52 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Do NOT use once the cause is already established, or for adding new behaviour — that is implementation, not diagnosis.

jasonm4130/claude-skills · 45 tokens

test-driven-development

Use when implementing any feature or bugfix, before writing implementation code. Do NOT use inside the subagent-driven-development loop, which runs its own per-task implement→review→fix cycle and supersedes this skill there.

jasonm4130/claude-skills · 48 tokens

adr

Use when the user knows what they want built and says "/adr", "write an ADR for X", "decide and build X", or "ADR-driven". Turns an intent into a grounded, cited, build-ready ADR at docs/adr/YYYY-MM-DD- .md — load-bearing decisions surfaced to the human — then hands off to the subagent-driven-development loop. For…

jasonm4130/claude-skills · 120 tokens

frontend-design

Guidance for distinctive, intentional frontend/UI design — aesthetic direction, typography, layout, motion, and copy — when building new UI or reshaping existing UI. Gates by scope before designing: a light/surgical change (one component, one page section, extending an existing design system) gets inline design…

jasonm4130/claude-skills · 218 tokens