domain-validator

domain-validator is a skill for Claude Code, Codex from jpantsjoha/ai-native-developer-experience. It costs 42 tokens per session (774 once invoked), scanned A, original, Apache-2.0.

A checking procedure that compares an agent’s claims with explicit domain rules and a trusted source of truth. Domain rules are the facts and limits that must hold in a particular area, such as finance or configuration.

In plain words
What is it for?
Use it after an agent produces factual output involving specialised data, before saving that output, or before sending it to another system or person.
Why use it?
It reduces the risk of passing unverified agent output into decisions, databases, documents, or user-facing results.

Skill for Claude CodeCodex

Part of the join-the-team plugin — 21 skills, 3 commands, 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/jpantsjoha/ai-native-developer-experience/domain-validator
Any agent
npx skills add jpantsjoha/ai-native-developer-experience --skill domain-validator
Clone the repo
git clone --depth 1 https://github.com/jpantsjoha/ai-native-developer-experience

Made for: Claude Code, Codex.

Or install join-the-team, the plugin that ships this one along with the rest of its 21 skills, 3 commands, 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 domain-validator

README.md
[![agentmods](https://agentmods.dev/badge/skills/jpantsjoha/ai-native-developer-experience/domain-validator.svg)](https://agentmods.dev/skills/jpantsjoha/ai-native-developer-experience/domain-validator)
Your own site
<a href="https://agentmods.dev/skills/jpantsjoha/ai-native-developer-experience/domain-validator"><img src="https://agentmods.dev/badge/skills/jpantsjoha/ai-native-developer-experience/domain-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 774 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 $0.00042 $0.00774
Opus 5 $0.00021 $0.00387
Sonnet 5 $0.00008 $0.00155
Haiku 4.5 $0.00004 $0.00077

Measured 5d ago against content hash 75cfc3b599db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

domain-validator 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.

skills/domain-validator/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Domain Validator

Agent output is a hypothesis. Domain validation is the test.

An agent that produces output without validation is a system that produces hallucinations at scale. The domain validator is the check that separates "the agent said so" from "it is true."

When to use

  • After an agent produces output that feeds a downstream system or human decision
  • When an agent has reasoned over domain-specific data (financial figures, medical records, legal clauses, system configurations)
  • Before persisting agent-generated content to a database or document store
  • When an agent output will be presented to an end user as factual

Procedure

  1. Declare the domain rules — before running any validation, the domain rules must be explicit:

    • What are the invariants? (e.g. "a date range must have start < end", "a price must be positive", "a configuration must reference an existing resource")
    • What are the allowed value ranges or enumerations?
    • What is the ground truth source? (database record, API response, regulatory document, schema definition)
  2. Extract the claims — identify the specific assertions in the agent output that are subject to validation. Not every word in the output is a claim; focus on structured data, named values, and factual assertions.

  3. Validate each claim against the domain rules:

    • Structural validation: does the output conform to the expected schema or format?
    • Range and constraint validation: are values within allowed bounds?
    • Referential integrity: do referenced entities exist in the ground truth source?
    • Logical consistency: are the claims internally consistent? (e.g. no contradictory figures)
    • Freshness: is the ground truth source current, or could it be stale?
  4. Classify findings:

    • PASS: claim is valid against all domain rules
    • WARN: claim is plausible but cannot be fully verified (e.g. ground truth unavailable)
    • FAIL: claim violates a domain rule or contradicts ground truth

Read the full file on GitHub · 64 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 · 64 lines · 42 tokens per session scan A 75cfc3b599db

Subscribe to this mod's changes

domain-validator is a skill published in the GitHub repository jpantsjoha/ai-native-developer-experience (11 stars, last pushed 28d ago), licensed Apache-2.0. It adds 42 tokens to every session and 774 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 2026-08-30.