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.
curl -O https://raw.githubusercontent.com/patrickdeanfox/zuar-portal-mcp/main/.claude/skills/db-modifications/SKILL.mdgit clone --depth 1 https://github.com/patrickdeanfox/zuar-portal-mcpWrote 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/patrickdeanfox/zuar-portal-mcp/db-modifications)<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.
<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>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 | $0.00247 | $0.06396 |
| Opus 5 | $0.00123 | $0.03198 |
| Sonnet 5 | $0.00049 | $0.01279 |
| Haiku 4.5 | $0.00025 | $0.00640 |
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.
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:
- Admin side (one-time setup). A Portal admin creates a row in the
db_modificationstable via the Portal's Swagger UI (/docs/). The row defines aname, optionalcredentials_id, asqltemplate with:named_params, and optionaldefault_params. This is the only way to register executable SQL. - Client side (runtime). Browser code in an HTML block POSTs to
/api/db_modifications/runwith the modification'snameand 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. |
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.
- 10d ago First seen · 615 lines · 247 tokens per session scan A c06892c16e33
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.
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.
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.
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…
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…
durable-objects
Build, debug, or review Cloudflare Durable Objects code for persistent state and coordination.
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…