review

review is a skill for Claude Code, Codex from sembraniteam/claude-plugins. It costs 172 tokens per session (9,672 once invoked), scanned A, original, MIT.

A workflow for reviewing an existing software architecture document, codebase, or both, then creating a revised version.

In plain words
What is it for?
Use it to audit an architecture, check for drift between design and code, present findings, and guide a versioned revision.
Why use it?
It provides a structured way to find design problems, compare the design with the implementation, and track architecture changes over time.

Skill for Claude CodeCodex

Part of the architecture-designer plugin — 3 skills, 13 agents 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/sembraniteam/claude-plugins/review
Any agent
npx skills add sembraniteam/claude-plugins --skill review
Clone the repo
git clone --depth 1 https://github.com/sembraniteam/claude-plugins

Made for: Claude Code, Codex.

Or install architecture-designer, the plugin that ships this one along with the rest of its 3 skills, 13 agents.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/sembraniteam/claude-plugins/review.svg)](https://agentmods.dev/skills/sembraniteam/claude-plugins/review)
Your own site
<a href="https://agentmods.dev/skills/sembraniteam/claude-plugins/review"><img src="https://agentmods.dev/badge/skills/sembraniteam/claude-plugins/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 172 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,672 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 5.1 $0.00172 $0.09672
Opus 5 $0.00086 $0.04836
Sonnet 5 $0.00034 $0.01934
Haiku 4.5 $0.00017 $0.00967

Measured 5d ago against content hash fe62f7e92c67, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 5d 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.

architecture-designer/skills/review/SKILL.md · 556 lines

How it starts

The opening of the file, as written. The whole thing — 556 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Architecture Designer — Review and Revision Workflow

This skill reviews an existing architecture (from a document, the codebase, or both), presents findings, and guides the user through a structured revision process that creates a new versioned document.

Scripts directory: see "Path resolution" at the bottom of this file.

References directory: this skill has none of its own — every design/references/... pointer below resolves into the sibling design skill's references/ directory, per "Path resolution" at the bottom of this file.


Before starting — load and validate session context

Check for docs/architecture-designer/session.json:

  • If the file exists: read it in full, then run python3 <scripts_dir>/validate-session.py and show its output — this is a hard gate; do not proceed to Step 1 until it reports SESSION CHECK PASSED. See design/references/session-schema.md section "Session completeness gate" for what the script checks and how to resolve a failure (e.g. running /architecture-designer:design to fill the gaps). The session contents are the original requirements baseline the architecture-reviewer and any revision agents review against.

  • Also check for an interrupted revision in progress: if session.json contains a progress key whose lastCompletedStep is anything before step11 (a document save) and its owner is "review", a previous revision session died mid-pipeline. Apply design/references/session-schema.md section "Resuming Steps 6a–13 via progress" to resume Step 4's revision flow from where it left off instead of restarting Step 4a — including validating any recorded reviewCycles verdicts' hashes and checking docs/architecture-designer/last-review.md for an unresolved fixer cycle. If progress.owner is instead "design" (or absent) with lastCompletedStep before step11, this is an original design pipeline that never finished — not a review revision — since review never touches progress before step 4b and no revision document was ever produced to revise. Do not attempt to resume Step 4 from this state (there is no revision scope, no document to list in Step 2a). Instead tell the user: "It looks like a previous /architecture-designer:design session didn't finish (no architecture document was ever saved). Run /architecture-designer:design to complete it before reviewing." and stop here rather than proceeding to Step 1.

Read the full file on GitHub · 556 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. 5d ago First seen · 556 lines · 172 tokens per session scan A fe62f7e92c67

Subscribe to this mod's changes

review is a skill published in the GitHub repository sembraniteam/claude-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 172 tokens to every session and 9,672 once invoked, about $0.0009 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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 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

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

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens