code-review-iterative

An iterative code-review workflow that asks three reviewers to examine the same changes from engineering, senior development, and testing perspectives. Code review is the process of checking code for defects and design problems before it is accepted.

In plain words
What is it for?
Use it to review unstaged changes, specified files, a branch, or a pull request, with findings labeled from blocker to minor note.
Why use it?
It helps reveal different kinds of problems and then repeats the review after fixes, with stricter thresholds each time.

Skill for Claude CodeCodex

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/mayank-io/mstack/code-review-iterative
Any agent
npx skills add mayank-io/mstack --skill code-review-iterative
Clone the repo
git clone --depth 1 https://github.com/mayank-io/mstack

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,162 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 $0.00047 $0.01162
Opus 5 $0.00023 $0.00581
Sonnet 5 $0.00009 $0.00232
Haiku 4.5 $0.00005 $0.00116

Measured yesterday against content hash ddbba1d14a11, 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-iterative 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 yesterday.

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/dev/skills/code-review-iterative/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Iterative Code Review

Run up to 4 review-fix iterations with 3 parallel reviewer agents (PE, Sr SDE, QA). Each iteration raises the bar for what gets fixed, converging quickly to clean code.

Review Scope

By default, review unstaged changes from git diff. If the user specifies files, a branch, or a PR, use that scope instead.

Process

Step 0: Initialize

Set iteration = 1. Determine the review scope (git diff, specific files, or user-specified).

Step 1: Launch 3 Reviewer Agents in Parallel

Dispatch 3 agents simultaneously, each reviewing the same code from a different perspective. Every agent MUST categorize each finding as exactly one of: BLOCKER, HIGH, MEDIUM, LOW, NIT.

Agent 1 — Principal Engineer (PE):

Review this code as a Principal Engineer. Focus on: architecture, design patterns, abstraction quality, API contracts, performance implications, scalability concerns, and whether the approach is fundamentally sound. Categorize every finding as BLOCKER, HIGH, MEDIUM, LOW, or NIT. Include file path and line number for each.

Stay in your lane: You own architecture, AST/IR design, parser/compiler structure, and performance. Do NOT rule on whether a domain concept is semantically valid or whether a condition should accept certain inputs from a domain perspective — that is the Domain Expert's call. If you think a domain assumption in the code is wrong, flag it as a question rather than a finding.

Agent 2 — Senior SDE:

Review this code as a Senior Software Engineer. Focus on: correctness, edge cases, error handling, null/undefined safety, race conditions, resource leaks, naming, readability, DRY violations, and adherence to project conventions (check CLAUDE.md). Categorize every finding as BLOCKER, HIGH, MEDIUM, LOW, or NIT. Include file path and line number for each.

Stay in your lane: You own implementation correctness, code quality, and codebase consistency. Do NOT rule on domain semantics or override domain-driven design decisions. If a pattern seems wrong but is documented as a domain requirement, flag it as a question rather than a finding.

Read the full file on GitHub · 97 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. yesterday First seen · 97 lines · 47 tokens per session scan A ddbba1d14a11

Subscribe to this mod's changes

code-review-iterative is a skill published in the GitHub repository mayank-io/mstack (5 stars, last pushed 7d ago), licensed MIT. It adds 47 tokens to every session and 1,162 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens