agentmods.dev

review-zod-integration

review-zod-integration is a skill for Claude Code, Codex from patternfly/patternfly-mcp. It costs 87 tokens per session (1,451 once invoked), scanned A, original, MIT.

A review workflow for Zod dependency upgrades in the PatternFly MCP project. Zod is a TypeScript library that checks and parses data at runtime.

In plain words
What is it for?
Comparing release notes with project usage, running tests, and writing a dated impact report with prioritized fixes.
Why use it?
It identifies how a Zod version change may affect the code before or during an upgrade.

Skill for Claude CodeCodex

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

not rated 5repo changed 1mo ago A scan 87 tokens original MIT

Good fit Comparing release notes with project usage, running tests, and writing a dated impact report with prioritized fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/patternfly/patternfly-mcp/review-zod-integration
View source ↗ patternfly/patternfly-mcp
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 patternfly/patternfly-mcp --skill review-zod-integration
Clone the repo
git clone --depth 1 https://github.com/patternfly/patternfly-mcp

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 review-zod-integration

README.md
[![agentmods](https://agentmods.dev/badge/skills/patternfly/patternfly-mcp/review-zod-integration/github.svg)](https://agentmods.dev/skills/patternfly/patternfly-mcp/review-zod-integration)
Your own site
<a href="https://agentmods.dev/skills/patternfly/patternfly-mcp/review-zod-integration"><img src="https://agentmods.dev/badge/skills/patternfly/patternfly-mcp/review-zod-integration/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review-zod-integration

Your own site · 80×15
<a href="https://agentmods.dev/skills/patternfly/patternfly-mcp/review-zod-integration"><img src="https://agentmods.dev/badge/skills/patternfly/patternfly-mcp/review-zod-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,451 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 $0.00087 $0.01451
Opus 5.5 $0.00035 $0.00580
Sonnet 5.5 $0.00017 $0.00290
Haiku 4.5 $0.00009 $0.00145

Measured 1mo ago against content hash 33dcb3ee3dd8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-zod-integration 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 1mo 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.

guidelines/skills/review-zod-integration/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Zod Integration (PatternFly MCP)

When to use

  • User bumps or proposes bumping zod in package.json
  • User asks for a Zod upgrade review, integration review, or impact analysis
  • Dependabot/Renovate PR for zod
  • User wants a report comparing Zod release notes to this codebase

Workflow

  1. Versions and release notes

    • Read package.json, package-lock.json, and node_modules/zod/package.json if installed.
    • Note previous version from git log -1 -- package.json or the bump PR/commit.
    • Fetch release notes for the target minor/major (release page, GitHub API, packaged changelog, or any fetch tool): https://github.com/colinhacks/zod/releases/tag/v{VERSION}.
    • For patch bumps within the same minor (e.g. 4.4.1 → 4.4.3), use the minor release notes (e.g. v4.4.0) plus patch-specific notes when present.
    • Offline fallback: If release notes cannot be retrieved, state that limitation and continue from package.json, lockfile, and the inventory/audit steps only.
    • Extract potentially breaking, other fixes, performance, and locales sections.
    • If notes are ambiguous or the bump is minor/major, follow reference.md — Audit depth policy (prefer node_modules/zod/src/ when shipped; otherwise published entry points from package.json exports).

  2. Repo guidelines

    • Read (do not paste into the report): CONTRIBUTING.md, guidelines/agent_coding.md, guidelines/agent_testing.md, docs/development.md.

  3. Codebase inventory

Read the full file on GitHub · 79 lines

Files

What ships with it

1 file 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. 1mo ago Changed · +1 lines 33dcb3ee3dd8
  2. 2mo ago First seen · 78 lines · 87 tokens per session scan A 2462a2a6a4dd

Subscribe to this mod's changes

review-zod-integration is a skill published in the GitHub repository patternfly/patternfly-mcp (5 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 1,451 once invoked, about $0.0003 per session on Opus 5.5. 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.

Code reviewLanguagesTypeScript
Related

review-zod-integration compared with skills from other repositories

review-zod-integration next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
review-zod-integrationpatternfly/patternfly-mcpSkill52d agoMITA87Claude Code, Codex
no-bare-castsprisma/ormSkill48kyesterdayApache-2.0A52Claude Code, Codex
coding-standardshashgraph-online/awesome-codex-pluginsSkill1.5kyesterdayApache-2.0A28Claude Code, Codex
splitting-oversized-modulesPostHog/posthogSkill41kyesterdaynoneA197Claude Code, Codex
best-practicesFradSer/dotclaudeSkill5962d agoMITA52Claude Code
plankton-code-qualityloulanyue/awesome-claude-notesSkill2711mo agoMITA34Claude Code
architecture-auditorg2AI/ORG2Skill2.6k3d agoAGPL-3.0A70Claude Code, Codex