code-review

code-review is a skill for Claude Code, Codex from contentstack/contentstack-ios. It costs 32 tokens per session (624 once invoked), scanned A, original, MIT.

A code-review checklist for an iOS software development kit. It checks public API design, errors, compatibility, dependencies, security, and test quality before or during a pull request review.

In plain words
What is it for?
Use it to review another developer's pull request or check your own changes before submitting them. It is specific to the Contentstack iOS content delivery SDK.
Why use it?
It helps reviewers find changes that could break existing users, weaken reliability, or fail project standards. A pull request is a proposed code change submitted for review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review another developer's pull request or check your own changes before submitting them. It is specific to the Contentstack iOS content delivery SDK.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/contentstack/contentstack-ios/code-review
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.

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

Made for: Claude Code, Codex.

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/contentstack/contentstack-ios/code-review.svg)](https://agentmods.dev/skills/contentstack/contentstack-ios/code-review)
Your own site
<a href="https://agentmods.dev/skills/contentstack/contentstack-ios/code-review"><img src="https://agentmods.dev/badge/skills/contentstack/contentstack-ios/code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 624 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 $0.00032 $0.00624
Opus 5 $0.00016 $0.00312
Sonnet 5 $0.00006 $0.00125
Haiku 4.5 $0.00003 $0.00062

Measured 3d ago against content hash dcc1b9ece62f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 3d 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/code-review/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review – Contentstack iOS CDA SDK

Use this skill when performing or preparing a pull request review for the iOS CDA SDK.

When to use

  • Reviewing someone else’s PR.
  • Self-reviewing your own PR before submission.
  • Checking that changes meet project standards (API, errors, compatibility, tests, security).

Instructions

Work through the checklist below. Optionally tag items with severity: Blocker, Major, Minor. The canonical short checklist lives in .cursor/rules/code-review.mdc (aligned with contentstack-java and other CDA SDKs).

1. API design and stability

  • Public API: New or changed public headers are necessary and documented (header comments / usage examples consistent with the repo).
  • Backward compatibility: No breaking changes to public Objective-C / Swift-visible API without agreement (major version or explicit migration).
  • Naming: Consistent with existing SDK and CDA terminology (Stack, Entry, Query, Config, etc.).

Severity: Breaking public API without approval = Blocker. Missing docs on new public API = Major.

2. Error handling and robustness

  • Errors: Failures use NSError, failure blocks, or delegates as appropriate for the module.
  • Nullability: Annotations remain correct; no ignored errors in new code paths.
  • Memory / concurrency: No obvious retain cycles; threading matches existing networking patterns.

Severity: Wrong or missing error handling in new code = Major.

3. Dependencies and security

  • Dependencies: Podspec / vendored code changes are justified; versions do not introduce known critical issues.
  • SCA: Security findings (Snyk, Dependabot, etc.) are addressed or tracked.

Severity: New critical/high vulnerability = Blocker.

4. Testing

  • Coverage: New or modified behavior has XCTest coverage where feasible.
  • Conventions: Test classes follow *Test naming; async tests use expectations and sane timeouts.
  • Quality: Tests are deterministic and readable.

Read the full file on GitHub · 61 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. 3d ago First seen · 61 lines · 32 tokens per session scan A dcc1b9ece62f

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository contentstack/contentstack-ios (3 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 624 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 2026-09-04.

Related

Other skills, from other repositories