Atlas / Skills / jeremylongshore / Clay Architecture Variants

Clay Architecture VariantsSAFE

skills/jeremylongshore/clay-architecture-variants

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
1.14.0
Hosts
1 documented
License
MIT
Stars
2,823
01

Overview

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Read from source at commit 4f83675ca38aOBSERVED · 2026-10-08
02

Host compatibility

What the documentation claims. We have not run a compatibility test.

HostStatusNotes
claude-codementioned
03

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: clay-architecture-variants
description: 'Choose and implement Clay integration architecture for different scales
  and use cases.

  Use when designing new Clay integrations, comparing direct vs queue-based vs event-driven,

  or planning architecture for Clay-powered data operations.

  Trigger with phrases like "clay architecture", "clay blueprint",

  "how to structure clay", "clay integration design", "clay event-driven".

  '
allowed-tools: Read, Write, Edit, Grep
version: 1.14.0
license: MIT
author: Jeremy Longshore <[email protected]>
tags:
- saas
- clay
- migration
- scaling
compatibility: Designed for Claude Code
---
# Clay Architecture Variants

## Overview

Three proven architecture patterns for Clay data enrichment at different scales. Clay is a hosted SaaS -- your architecture decisions focus on how you send data in (webhooks), how you get enriched data out (HTTP API columns, CRM sync, or CSV export), and how you orchestrate the flow.

## Prerequisites

- Clay account with appropriate plan tier
- Clear understanding of data volume and latency requirements
- Infrastructure for chosen architecture tier (if queue-based or event-driven)

## Instructions

### Architecture 1: Direct Integration (Simple)

**Best for:** Small teams, < 1K enrichments/day, ad-hoc usage.

```
┌──────────────┐     webhook     ┌───────────┐
│ Your App     │───────POST─────>│ Clay Table │
│ (or CSV)     │                 │ (enriches) │
└──────────────┘                 └─────┬─────┘
                                       │
                                  CRM action
                                  or CSV export
                                       │
                                       v
                                 ┌───────────┐
                                 │ CRM / DB  │
                                 └───────────┘
```

```typescript
// Direct: send leads synchronously, export results manually
async function directEnrich(leads: Lead[]): Promise<void> {
  for (const lead of leads) {
    await fetch(process.env.CLAY_WEBHOOK_URL!, {
      method: 'POST',
      headers: { 'Content-Type': 'application/json' },
      body: JSON.stringify(lead),
    });
    await new Promise(r => setTimeout(r, 250)); // Rate limit
  }
  console.log(`Sent ${leads.length} leads. Check Clay table for enriched data.`);
  // Enriched data reaches CRM via Clay's native CRM action column
}
```

**Pros:** Zero infrastructure, 5-minute setup, works on all Clay plans.
**Cons:** No retry logic, no programmatic access to enriched data, manual export only.

---

### Architecture 2: Webhook-in, HTTP API-out (Standard)

**Best for:** Growing teams, 1K-10K enrichments/day, CRM integration.

```
┌──────────────┐     webhook     ┌───────────┐   HTTP API col   ┌──────────────┐
│ Your App     │───────POST─────>│ Clay Table │──────POST──────>│ Your Webhook │
│              │                 │ (enriches) │                 │ Handler      │
└──────────────┘                 └───────────┘                 └──────┬───────┘
                                                                      │
                                                                 Process +
                                                                 Route
                                                                      │
                                                          ┌───────────┼───────────┐
                                                          │           │           │
                                                          v           v           v
                                                       ┌─────┐   ┌───────┐   ┌──────┐
                                                       │ CRM │   │Outreach│  │ DB   │
                                                       └─────┘   └───────┘   └──────┘
```

```typescript
// Standard: send leads via webhook, receive enriched data via HTTP API column
// Inbound: Your app -> Clay
async function sendLeads(leads: Lead[]): Promise<void> {
  const batchResult = await clayClient.sendBatch(leads, 200);
  console.log(`Sent: ${batchResult.sent}, Failed: ${batchResult.failed}`);
}

// Outbound: Clay HTTP API column -> Your webhook handler
app.post('/api/clay/enriched', async (req, res) => {
  res.json({ ok: true }); // Respond fast

  const lead = req.body;
  if (lead.icp_score >= 80 && lead.work_email) {
    await pushToCRM(lead);
    await addToOutreachSequence(lead);
  } else if (lead.icp_score >= 50) {
    await addToNurtureCampaign(lead);
  }
});
```

**Pros:** Full automation, programmatic access to enriched data, flexible routing.
**Cons:** Requires Growth plan (HTTP API columns), needs public HTTPS endpoint.

---

### Architecture 3: Queue-Based Pipeline (Scale)

**Best for:** Enterprise, 10K+ enrichments/day, multiple data sources.

```
┌───────────┐
│ Web Forms │──┐
└───────────┘  │     ┌───────────┐     webhook     ┌───────────┐
               ├────>│ Job Queue │───────POST─────>│ Clay Table │
┌───────────┐  │     │ (BullMQ)  │                 │ (enriches) │
│ CRM Events│──┘     └───────────┘                 └─────┬─────┘
└───────────┘              │                              │
                      DLQ on fail                   HTTP API col
┌───────────┐              │                              │
│ CSV Import│──────────────┘                              v
└───────────┘                                   ┌──────────────┐
                                                │ Your Handler │
                                                │ (w/ circuit  │
                                                │  breaker)    │
                                                └──────┬───────┘
                                                       │
                                            ┌──────────┼──────────┐
                                            │          │          │
                                            v          v          v
                               
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 4f83675ca38afull audit observations/trust-audit/skill/jeremylongshore__clay-architecture-variants.json · Report an issue / request a re-scan
05

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-084f83675ca38aSAFEB89first audit
06

Questions

What does the Clay Architecture Variants skill do?

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Is Clay Architecture Variants safe to install?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.

What can Clay Architecture Variants access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

Which assistants does Clay Architecture Variants work with?

Its documentation mentions claude-code. That is what the text claims, not a compatibility test we ran.

How current is this page?

The grade is for one exact copy of the source (4f83675ca38a), read on 2026-10-08. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement