zuar-portal-mcp: Skill for Claude Code

.claude/skills/db-modifications/SKILL.md

db-modifications is a skill for Claude Code from patrickdeanfox/zuar-portal-mcp. It costs 247 tokens per session (6,396 once invoked), scanned A, original, MIT.

A guide to Zuar Portal's approved database-write service, which lets browser code run predefined database statements. Portal administrators define the statements, while page code supplies only named values.

In plain words
What is it for?
Use it when building Portal blocks that insert, update, delete, or upsert data in Portal's local database or a connected external database.
Why use it?
It lets pages save, change, remove, or merge data without sending raw SQL from the browser, reducing the risk of unauthorized statements and SQL injection.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is patrickdeanfox/zuar-portal-mcp's own configuration. It tells Claude Code how to work on zuar-portal-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything zuar-portal-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to patrickdeanfox/zuar-portal-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/patrickdeanfox/zuar-portal-mcp/main/.claude/skills/db-modifications/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/patrickdeanfox/zuar-portal-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for db-modifications

README.md
[![agentmods](https://agentmods.dev/badge/skills/patrickdeanfox/zuar-portal-mcp/db-modifications/github.svg)](https://agentmods.dev/skills/patrickdeanfox/zuar-portal-mcp/db-modifications)
Your own site
<a href="https://agentmods.dev/skills/patrickdeanfox/zuar-portal-mcp/db-modifications"><img src="https://agentmods.dev/badge/skills/patrickdeanfox/zuar-portal-mcp/db-modifications/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.

agentmods 80×15 button for db-modifications

Your own site · 80×15
<a href="https://agentmods.dev/skills/patrickdeanfox/zuar-portal-mcp/db-modifications"><img src="https://agentmods.dev/badge/skills/patrickdeanfox/zuar-portal-mcp/db-modifications.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 247 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,396 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00247 $0.06396
Opus 5 $0.00123 $0.03198
Sonnet 5 $0.00049 $0.01279
Haiku 4.5 $0.00025 $0.00640

Measured 10d ago against content hash c06892c16e33, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

db-modifications 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 10d 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.

.claude/skills/db-modifications/SKILL.md · 615 lines

How it starts

The opening of the file, as written. The whole thing — 615 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Zuar Portal db_modifications Service

The db_modifications service is how browser-based code inside a Zuar Portal writes data back to a database — Portal's local Postgres or any external database reachable via Portal credentials. Every write is pre-defined by a Portal admin as a named SQL template, so client code can only execute approved statements. SQL injection is impossible because the client never sends SQL.

Use this skill whenever the user needs to save, insert, update, delete, or upsert data from a portal page, whether they're building the block itself or setting up the underlying modification.


Mental Model — How It Works

Two sides to every db_modifications task:

  1. Admin side (one-time setup). A Portal admin creates a row in the db_modifications table via the Portal's Swagger UI (/docs/). The row defines a name, optional credentials_id, a sql template with :named_params, and optional default_params. This is the only way to register executable SQL.
  2. Client side (runtime). Browser code in an HTML block POSTs to /api/db_modifications/run with the modification's name and the parameter values. Authentication is automatic via the user's JWT cookie — do not send an Authorization header.

If the user asks "how do I insert from a block?" they need both sides. Always confirm the modification exists (or needs to be created) before writing client code.


The db_modifications Table

create table public.db_modifications (
  id              uuid         not null primary key,
  name            varchar(256) not null unique,
  credentials_id  varchar(256),
  sql             text,
  default_params  text,
  updated_at      timestamp with time zone not null,
  created_at      timestamp with time zone not null
);
Column Purpose
id UUID. Either this or name identifies a modification in API calls.
name Unique human-readable identifier. Preferred in client code — more readable than a UUID.
credentials_id ID or name of a Portal credential for the target database. null → Portal's local Postgres.
sql One or more SQL statements, each ending in ;. Named parameters use :name syntax. Must be in the target DB's dialect.
default_params JSON object of default values. Used when the client POST omits a parameter.

Read the full file on GitHub · 615 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. 10d ago First seen · 615 lines · 247 tokens per session scan A c06892c16e33

Subscribe to this mod's changes

db-modifications is a skill published in the GitHub repository patrickdeanfox/zuar-portal-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 247 tokens to every session and 6,396 once invoked, about $0.0012 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 skills, from other repositories

event-store-design

Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.

wshobson/agents · 33 tokens

convex-explain-app

Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.

openclaw/clawhub · 47 tokens

platform-custom-field-generate

Use this skill when users need to create, generate, or validate Salesforce Custom Field metadata. Trigger when users mention custom fields, field types, Roll-up Summary fields, Master-Detail relationships, Lookup relationships, formula fields, picklists, dependent (controlling) picklists, referencing a value set from…

forcedotcom/sf-skills · 194 tokens

field-service-sobject-create-configure

Headless 360 REST API deployment step for creating sObject records. Handles describe-based field discovery, required-field derivation, entity-relationship ordering, and composite graph transactions. Use this skill when a designer skill (or a user directly) needs to create sObject records after design confirmation…

forcedotcom/sf-skills · 74 tokens

durable-objects

Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.

fcakyon/claude-codex-settings · 22 tokens

nornicdb-grpc

Drive NornicDB over gRPC — the Qdrant-compatible surface (Collections, Points, Snapshots) plus the additive NornicSearch service. Use when ingesting via Qdrant SDKs, migrating from Qdrant, or running hybrid text+vector search from a non-Bolt client. Covers connection, RPC catalog, collection→database mapping…

orneryd/NornicDB · 98 tokens