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 skills add shennawardana23/skillme --skill erd-expertgit clone --depth 1 https://github.com/shennawardana23/skillmeWrote 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/shennawardana23/skillme/erd-expert)<a href="https://agentmods.dev/skills/shennawardana23/skillme/erd-expert"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/erd-expert/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/skills/shennawardana23/skillme/erd-expert"><img src="https://agentmods.dev/badge/skills/shennawardana23/skillme/erd-expert.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 | $0.00100 | $0.02190 |
| Opus 5 | $0.00050 | $0.01095 |
| Sonnet 5 | $0.00020 | $0.00438 |
| Haiku 4.5 | $0.00010 | $0.00219 |
Grade A, and why
erd-expert 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 11d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ERD Expert — Hotel Domain Schema Design
Entity-relationship design for the hotel domain, targeting PostgreSQL and
this organization's Sentec platform (Sentec PMS, Sentec Booking Engine,
Sentec EMS). For the mechanics of keeping queries and migrations
partition-safe once a table exists, see postgres-hotel-partitioning —
this skill covers designing the ERD itself; that one covers querying and
migrating it correctly afterward. For index/data-type choices beyond what's
listed here, see postgres-patterns.
Core hotel-domain entities
| Entity | Partition key | Key relationships |
|---|---|---|
hotel |
— | root anchor; every partitioned table's hotel_id FKs here conceptually (not enforceable as a literal FK across partitions in all cases — validate in application logic) |
room |
hotel_id |
belongs to a hotel, has a room_type |
reservation |
hotel_id |
references guest, hotel, room; carries a status state machine |
guest |
hotel_id |
PII-sensitive; has a loyalty_tier |
rate_plan |
hotel_id |
pricing rules, scoped per channel |
channel |
— | small reference table: OTA | DIRECT | GDS | WHOLESALER |
folio |
hotel_id |
billing record linked to a reservation |
Reservation state machine
PENDING → CONFIRMED → CHECKED_IN → CHECKED_OUT
↘ CANCELLED (from PENDING or CONFIRMED)
↘ NO_SHOW (from CONFIRMED)
Model this as a CHECK constraint or enum on status, plus an audit
table (reservation_status_history) if the transition history itself
must be queryable — don't try to derive "when did this become CONFIRMED"
from updated_at on the mutable row alone.
Required columns and conventions
Every table in the hotel domain carries these columns, matching the convention already established for partitioned tables:
id bigint GENERATED ALWAYS AS IDENTITY,
hotel_id integer NOT NULL, -- partition key (LIST partitioning)
created_at timestamptz NOT NULL DEFAULT now(),
updated_at timestamptz NOT NULL DEFAULT now(),
PRIMARY KEY (hotel_id, id)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 199 lines · 100 tokens per session scan A 76172e56b20c
erd-expert is a skill published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 13d ago), licensed Apache-2.0. It adds 100 tokens to every session and 2,190 once invoked, about $0.0005 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.
Other skills, from other repositories
postgresql-development-cloudbase
Use when building, debugging, or evaluating CloudBase PostgreSQL / CloudBase PG / PG mode apps, including Postgres schema setup, queryPgDatabase/managePgDatabase, JS SDK v3 app.rdb() CRUD/RPC, PG HTTP API fallback, RLS-style permissions, username-password auth, and Web CMS/admin CRUD flows backed by CloudBase PG.
database-architecture
MANDATORY when designing schemas, writing migrations, creating indexes, or making architectural database decisions - enforces PostgreSQL 18 best practices including AIO, UUIDv7, temporal constraints, and modern indexing strategies.
timescaledb
MANDATORY when working with time-series data, hypertables, continuous aggregates, or compression - enforces TimescaleDB 2.24.0 best practices including lightning-fast recompression, UUIDv7 continuous aggregates, and Direct Compress.
postgis
MANDATORY when working with geographic data, spatial queries, geometry operations, or location-based features - enforces PostGIS 3.6.1 best practices including STCoverageClean, SFCGAL 3D functions, and bigint topology.
postgres-rls
MANDATORY when touching auth tables, tenant isolation, RLS policies, or multi-tenant database code - enforces Row Level Security best practices and catches common bypass vulnerabilities.
alloydb-basics
Manages clusters, instances, and backups for AlloyDB for PostgreSQL, and integrates with AlloyDB Model Context Protocol (MCP) tools for automated database operations. Use when creating, configuring, or administering AlloyDB databases. Do NOT use for general PostgreSQL instances (e.g. Cloud SQL) or other GCP databases.