reviewing-code

reviewing-code is a skill for Claude Code, Codex from nexus-substrate/nexus-agents. It costs 93 tokens per session (2,440 once invoked), scanned A, original, MIT.

A code-review procedure for checking someone else's changes after they appear in a pull request or commit. It checks correctness, readability, architecture, tests, and security against project standards.

In plain words
What is it for?
Use it to review pull requests, audit committed changes, check implementation quality, or perform a blind pre-merge review. It is separate from self-critique, which is for reviewing your own work before submission.
Why use it?
It provides a consistent review gate before merging and helps catch missing edge cases, weak tests, style problems, architectural inconsistencies, and security risks.

Skill for Claude CodeCodex

Part of the nexus-agents plugin — 33 skills, 16 agents, 1 hook 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/nexus-substrate/nexus-agents/reviewing-code
Any agent
npx skills add nexus-substrate/nexus-agents --skill reviewing-code
Clone the repo
git clone --depth 1 https://github.com/nexus-substrate/nexus-agents

Made for: Claude Code, Codex.

Or install nexus-agents, the plugin that ships this one along with the rest of its 33 skills, 16 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 reviewing-code

README.md
[![agentmods](https://agentmods.dev/badge/skills/nexus-substrate/nexus-agents/reviewing-code.svg)](https://agentmods.dev/skills/nexus-substrate/nexus-agents/reviewing-code)
Your own site
<a href="https://agentmods.dev/skills/nexus-substrate/nexus-agents/reviewing-code"><img src="https://agentmods.dev/badge/skills/nexus-substrate/nexus-agents/reviewing-code.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,440 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 $0.00093 $0.02440
Opus 5 $0.00046 $0.01220
Sonnet 5 $0.00019 $0.00488
Haiku 4.5 $0.00009 $0.00244

Measured 4d ago against content hash a069250809cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reviewing-code 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.

skills/reviewing-code/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Skill

Pre-emit vs post-hoc

This skill is the post-hoc review gate — evaluating someone else's diff after it lands as a PR. The complementary pre-emit gate is self-critique, which the author runs on their own work before submitting:

Skill Reviews When
self-critique Your own output Before you emit anything
reviewing-code (this) Others' code (PRs, commits) After someone else writes code

Both use the same five-axis framework below. Both can apply to the same artifact at different lifecycle points — author self-critiques before PR; reviewer applies this skill on the resulting diff.

Five-axis review framework

Evaluate every change across these dimensions. The order matters — correctness gates merge; the rest are quality.

  1. Correctness — does the code do what the spec says? Are edge cases (null, empty, boundary, error paths) handled? Are the tests actually testing the behavior, not just the implementation?
  2. Readability — would another engineer understand this without explanation? Names follow project conventions? Control flow straightforward?
  3. Architecture — does it follow existing canonical patterns (CLAUDE.md "Canonical Paths") or introduce a new one? Module boundaries respected? No circular deps? Abstraction level appropriate?
  4. Security — input validated at boundaries (per .rules/untrusted-input.md)? Secrets out of code/logs? Auth/authz where needed? Parameterized queries? See security-checklist.
  5. Performance — N+1 patterns? Unbounded data fetching? Sync I/O in hot paths? Re-render storms? Missing pagination? Don't optimize without evidence — see performance-optimization skill.

Read the full file on GitHub · 207 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. 4d ago First seen · 207 lines · 93 tokens per session scan A a069250809cb

Subscribe to this mod's changes

reviewing-code is a skill published in the GitHub repository nexus-substrate/nexus-agents (18 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 2,440 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

tooluniverse-drug-research

Comprehensive drug profiling — mechanism, primary/secondary targets, drug interactions, clinical-trial status, adverse events (FAERS), pharmacogenomics, and approval history. Use for full drug investigation reports, 'tell me about drug X' queries, and assembling drug profiles for clinicians, researchers, or regulatory…

mims-harvard/ToolUniverse · 71 tokens

x-scorecard

OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.

x-cmd/x-cmd · 57 tokens

memstack-business-gdpr

Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…

cwinvestments/memstack · 121 tokens

catalyst-center-readonly

Query Cisco Catalyst Center read-only — device inventory, site hierarchy, wireless, assurance health, compliance, software images, events. All 514 read-only API operations reachable through 8 grouped dispatchers. Use when asked what Catalyst Center manages, where a device sits, what its health or compliance state is…

automateyournetwork/netclaw · 78 tokens

build-audit-logs

Build or review audit trails in TypeScript/JavaScript apps using evlog (pipelines, typed actions, denials, retention, compliance-style reviews). For application code, not for extending the evlog package.

activepieces/activepieces · 49 tokens

nda-review

Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…

LegalQuants/lq-ai · 79 tokens