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 agentmods add skills/jpantsjoha/ai-native-developer-experience/domain-validatornpx skills add jpantsjoha/ai-native-developer-experience --skill domain-validatorgit clone --depth 1 https://github.com/jpantsjoha/ai-native-developer-experienceWrote 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/jpantsjoha/ai-native-developer-experience/domain-validator)<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>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 | $0.00042 | $0.00774 |
| Opus 5 | $0.00021 | $0.00387 |
| Sonnet 5 | $0.00008 | $0.00155 |
| Haiku 4.5 | $0.00004 | $0.00077 |
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.
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
-
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)
-
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.
-
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?
-
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
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.
- 5d ago First seen · 64 lines · 42 tokens per session scan A 75cfc3b599db
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.
Other skills, from other repositories
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
comet-hotfix
Comet 预设 —— 通过 open-build-verify-archive 短流程修复已有行为 bug。.
comet-design
Comet Classic 阶段 2 —— 为 change 产出深度技术 Design Doc。.
comet-hotfix
Comet preset path: Bug fix / hotfix. Skip brainstorming, directly open → build → verify → archive. Applicable for behavior fixes, scenarios not involving new capability design.
comet-verify
Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.
comet-tweak
Comet preset path: Non-bug small changes (tweak). Skip brainstorming and full plan, directly open → lightweight build → light verify → archive. Applicable for copy, configuration, documentation or prompt local optimization.