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.
git clone --depth 1 https://github.com/rungchan2/frontend-skillsWrote 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/commands/rungchan2/frontend-skills/enforce-data-layer)<a href="https://agentmods.dev/commands/rungchan2/frontend-skills/enforce-data-layer"><img src="https://agentmods.dev/badge/commands/rungchan2/frontend-skills/enforce-data-layer/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/commands/rungchan2/frontend-skills/enforce-data-layer"><img src="https://agentmods.dev/badge/commands/rungchan2/frontend-skills/enforce-data-layer.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 | $0.00000 | $0.02798 |
| Opus 5.5 | $0.00000 | $0.01119 |
| Sonnet 5.5 | $0.00000 | $0.00560 |
| Haiku 4.5 | $0.00000 | $0.00280 |
Grade A, and why
enforce-data-layer 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 2mo 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 — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enforce Data Layer Separation
CRITICAL ARCHITECTURE RULE: This project follows strict data layer separation principles based on SOLID and encapsulation.
Architecture Rules (MUST FOLLOW)
1. Service Layer (/lib/services/)
- All Supabase queries MUST be defined here
- File naming:
{table-name}.tsor{feature-name}-service.ts - No Supabase client calls outside this layer
- Export pure functions that handle data operations
- ALL functions MUST have explicit return types defined
- ALL async functions MUST return Promise types
Type System Rules:
- Import types from
/types/models.tsand/types/enums.ts- NEVER define types inline - Reuse existing types whenever possible - Check
/types/before creating new types - If new types are needed, define them in
/types/directory first - Use Type Helpers:
StudentRow,StudentInsert,StudentUpdatefrom/types/models.ts
Example structure:
// /lib/services/students.ts
import { createClient } from '@/lib/supabase/client'
import type { StudentRow, StudentInsert } from '@/types/models' // ✅ Import from centralized types
// ✅ CORRECT - Explicit return type with Promise<T>
export async function getStudents(centerId: number): Promise<StudentRow[]> {
const supabase = createClient()
const { data, error } = await supabase
.from('students')
.select('*')
.eq('center_id', centerId)
if (error) throw error
return data
}
// ✅ CORRECT - Return type defined
export async function createStudent(studentData: StudentInsert): Promise<StudentRow> {
const supabase = createClient()
const { data, error } = await supabase
.from('students')
.insert(studentData)
.select()
.single()
if (error) throw error
return data
}
// ❌ WRONG - Missing return type
export async function deleteStudent(id: number) {
// ...
}
// ❌ WRONG - Inline type definition
export async function updateStudent(id: number, data: { name: string }): Promise<any> {
// Should import StudentUpdate from /types/models.ts
}
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.
- 2mo ago First seen · 396 lines · 0 tokens per session scan A 55abba1c5597
enforce-data-layer is a command published in the GitHub repository rungchan2/frontend-skills (2 stars, last pushed 6mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,798 tokens. 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.
enforce-data-layer compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| enforce-data-layerrungchan2/frontend-skills | Command | 2 | 6mo ago | Apache-2.0 | A | 0 | Claude Code |
| initfcakyon/claude-codex-settings | Command | 1.2k | today | Apache-2.0 | A | 0 | Claude Code |
| toh-connectwasintoh/toh-framework | Command | 96 | 2mo ago | MIT | A | 12 | Claude Code |
| model-createsmicolon/ai-kit | Command | 7 | 1mo ago | MIT | A | 13 | Claude Code |
| servicesmgd34msu/goodvibes-plugin | Command | 6 | 2mo ago | MIT | A | 33 | Claude Code |
| sparc-supabase-adminruvnet/ruv-FANN | Command | 387 | 3mo ago | MIT | A | 32 | Claude Code |
| trex.kind.add-fieldopenshift-online/agent-control-plane | Command | 13 | 5d ago | MIT | A | 0 | Claude Code |