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.
npx skills add jahands/prompts --skill zod-v4git clone --depth 1 https://github.com/jahands/promptsWrote 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.
[](https://agentmods.dev/skills/jahands/prompts/zod-v4)<a href="https://agentmods.dev/skills/jahands/prompts/zod-v4"><img src="https://agentmods.dev/badge/skills/jahands/prompts/zod-v4/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.
<a href="https://agentmods.dev/skills/jahands/prompts/zod-v4"><img src="https://agentmods.dev/badge/skills/jahands/prompts/zod-v4.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.01016 |
| Opus 5 | $0.00012 | $0.00508 |
| Sonnet 5 | $0.00005 | $0.00203 |
| Haiku 4.5 | $0.00002 | $0.00102 |
Grade A, and why
zod-v4 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zod v4 Guidelines
Type Inference
Every schema MUST have inferred type above it:
export type User = z.infer<typeof User>
export const User = z.object({...})
Requirements:
- ALWAYS place type above schema
- ALWAYS use same name for type & schema
- NEVER use "Schema" suffix
- ALWAYS use JSDoc (
/** */), never// - NO EXCEPTIONS - even for internal/helper schemas
String Validation
String validations are standalone functions:
// WRONG: z.string().email()
// RIGHT: z.email(), z.url(), z.uuid(), z.ip()
Error Messages
Use error param sparingly - Zod's defaults are excellent:
// WRONG: z.email({error: "Invalid email"}) // Redundant!
// RIGHT: z.email() // Zod says "Invalid email"
// RIGHT: Only for business logic:
z.string().refine((val) => /[A-Z]/.test(val), {
error: 'Must contain uppercase',
})
Number Types
- Use
z.number()for general numbers z.int()for integers only (notz.number().int())z.int32(),z.float64()for specific types- Numbers finite by default
Object Types
z.object()- strips unknowns (default)z.strictObject()- rejects extrasz.looseObject()- allows extras
Custom Validation
Use .check() for advanced validation, .refine() for simple validation:
Migration steps:
.superRefine()→.check()for advanced validation with multiple issues- In
.check():val→ctx.value,ctx.addIssue()→ctx.issues.push() z.ZodIssueCode.custom→'custom'string- Add
input: ctx.valueto issue object - Use
.refine()for simple boolean validation with single error
Error Formatting
z.prettifyError()- Human-readable formatz.treeifyError()- Tree structure format
Functions
Define function schemas with input/output types:
z.function({
input: [z.string()],
output: z.number(),
})
Records
z.record(keyType, valueType)
ISO Formats
z.iso.datetime()- ISO 8601 datetimez.iso.date()- ISO 8601 date
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.
- 12d ago First seen · 146 lines · 24 tokens per session scan A bc01721d1a27
zod-v4 is a skill published in the GitHub repository jahands/prompts (19 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 1,016 once invoked, about $0.0001 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.
Other skills, from other repositories
no-bare-casts
Writing as in TypeScript or TSX production code, modifying a file that contains a bare as cast, silencing a type error with a cast, encountering as unknown as, or reviewing a cast site.
aws-sst-development
SST v4 (Ion) expert for managing AWS resources as code with the Pulumi-backed framework.
league-akari-shard-development
Use when creating, extending, refactoring, splitting, or reviewing League Akari main or renderer shards, including shard file organization, controller/loader/executor/handler boundaries, naming conventions, renderer TSX usage, platform guards, and public contract compatibility.
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
fast-typescript-check
Keep www-sacred's TypeScript fast to type-check and fast to run. Use when touching the ASCII/canvas animation components (the only real per-frame code here), tightening type-check wall-clock, or auditing a change for runtime or compiler regressions. Scoped to this repo — a React 19 / Next.js 16 component library plus…
migrate-better-result-3
Migrate a TypeScript codebase from better-result 2.x to 3.0. Use when upgrading better-result across the TaggedError syntax, removed Result serialization helpers, recovery inference, matching, or retry APIs.