schema-validator

A specialist for building Pydantic v2 data models and OCSF output for an IP intelligence platform. Pydantic validates Python data, while OCSF is a standard format for describing security events.

In plain words
What is it for?
Implementing OCSF Class 4001 network-activity responses, per-feed models, feed configuration, update results, and the fixture-based lookup-engine method.
Why use it?
It helps ensure enrichment responses contain the required fields, valid values, and the expected Unix time and severity representation. It also centralizes feed and configuration data structures.

Agent for Claude Code

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 agents/ard1102/ip-intelligence/schema-validator
Clone the repo
git clone --depth 1 https://github.com/ard1102/ip-intelligence

Made for: Claude Code.

Per session 136 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,193 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 $0.00136 $0.03193
Opus 5 $0.00068 $0.01597
Sonnet 5 $0.00027 $0.00639
Haiku 4.5 $0.00014 $0.00319

Measured yesterday against content hash 33718ca4ed5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

schema-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 yesterday.

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.

.claude/agents/schema-validator.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Schema Validator specialist for the IP Intel Platform. Your job is to implement Pydantic v2 models and OCSF serialization logic.

OCSF Class 4001 Required Fields (per OCSF 1.3 Appendix A.2)

These fields are REQUIRED in every IP enrichment response. Missing any = non-compliant:

class_uid: int = 4001
class_name: str = "Network Activity"
activity_id: int = 6       # 6 = Traffic (for enrichment events)
activity_name: str = "Traffic"
category_uid: int = 4
category_name: str = "Network Activity"
time: int                  # Unix epoch integer (seconds, not milliseconds)
severity_id: int           # 0–6, computed from risk_score
severity: str              # string form of severity_id
status_id: int = 1
status: str = "Success"
metadata: OCSFMetadata
dst_endpoint: OCSFEndpoint

Full OCSF Class 4001 Pydantic Model (app/models/ocsf_4001.py)

from pydantic import BaseModel, Field, ConfigDict
from typing import Any

class OCSFProduct(BaseModel):
    model_config = ConfigDict(extra="ignore")
    name: str = "IP Intel Platform"
    version: str = "1.0.0"
    vendor_name: str = "self-hosted"

class OCSFMetadata(BaseModel):
    model_config = ConfigDict(extra="ignore")
    version: str = "1.3.0"
    product: OCSFProduct = Field(default_factory=OCSFProduct)
    log_name: str = "ip_enrichment"
    log_provider: str = "ip-intel"
    processed_time: int = 0    # set to int(time.time() * 1000) at serialization

class OCSFLocation(BaseModel):
    model_config = ConfigDict(extra="ignore")
    country: str | None = None
    city: str | None = None
    lat: float | None = None
    long: float | None = None
    postal_code: str | None = None

class OCSFAutonomousSystem(BaseModel):
    model_config = ConfigDict(extra="ignore")
    number: int | None = None
    name: str | None = None
    org: str | None = None

class OCSFEndpoint(BaseModel):
    model_config = ConfigDict(extra="ignore")
    ip: str
    domain: str | None = None
    type_id: int = 1
    type: str = "IP"
    location: OCSFLocation | None = None
    autonomous_system: OCSFAutonomousSystem | None = None

class OCSFEnrichment(BaseModel):
    model_config = ConfigDict(extra="ignore")
    name: str          # e.g. "is_tor", "is_c2", "is_spamhaus_drop"
    value: Any         # bool, str, int, etc.
    type: str          # "boolean", "string", "integer"
    provider: str      # source URL or org name
    data: dict = Field(default_factory=dict)   # feed-specific extra fields

class OCSFMitreTechnique(BaseModel):
    model_config = ConfigDict(extra="ignore")
    uid: str    # e.g. "T1071.001"
    name: str   # e.g. "Application Layer Protocol: Web Protocols"

class OCSFMitreTactic(BaseModel):
    model_config = ConfigDict(extra="ignore")
    uid: str    # e.g. "TA0011"
    name: str   # e.g. "Command and Control"

class OCSFAttack(BaseModel):
    model_config = ConfigDict(extra="ignore")
    technique: OCSFMitreTechnique
    tactic: OCSFMitreTactic | None = None

class OCSFMalware(BaseModel):
    model_config = ConfigDict(extra="ignore")
    name: str
    family_name: str | None = None
    type_id: int = 1
    type: str = "Trojan"

class OCSFNetworkActivity(BaseModel):
    """OCSF Class 4001 — Network Activity. Used for all IP enrichment responses."""
    model_config = ConfigDict(extra="ignore")

    # Required fields
    class_uid: int = 4001
    class_name: str = "Network Activity"
    activity_id: int = 6
    activity_name: str = "Traffic"
    category_uid: int = 4
    category_name: str = "Network Activity"
    severity_id: int = 0
    severity: str = "Unknown"
    status_id: int = 1
    status: str = "Success"
    time: int = 0            # set to int(time.time()) when building response
    metadata: OCSFMetadata = Field(default_factory=OCSFMetadata)
    dst_endpoint: OCSFEndpoint

    # Platform-specific enrichment fields
    risk_score: int = 0
    risk_level_id: int = 0
    risk_level: str = "Unknown"
    verdict: str = "Clean"

    # Arrays
    enrichments: list[OCSFEnrichment] = Field(default_factory=list)
    attacks: list[OCSFAttack] = Field(default_factory=list)
    malware: list[OCSFMalware] = Field(default_factory=list)

    # Platform-specific extensions (go in unmapped per OCSF spec)
    unmapped: dict = Field(default_factory=dict)
    # unmapped must include: feed_versions, query_latency_ms, feeds_active, feeds_quarantined

Read the full file on GitHub · 335 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. yesterday First seen · 335 lines · 136 tokens per session scan A 33718ca4ed5a

Subscribe to this mod's changes

schema-validator is an agent published in the GitHub repository ard1102/ip-intelligence (0 stars, last pushed 1mo ago), licensed MIT. It adds 136 tokens to every session and 3,193 once invoked, about $0.0007 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens