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 agentmods add skills/delphicleancode/delphi-spec-kit/firebird-databasenpx skills add delphicleancode/delphi-spec-kit --skill firebird-databasegit clone --depth 1 https://github.com/delphicleancode/delphi-spec-kitWrote 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/delphicleancode/delphi-spec-kit/firebird-database)<a href="https://agentmods.dev/skills/delphicleancode/delphi-spec-kit/firebird-database"><img src="https://agentmods.dev/badge/skills/delphicleancode/delphi-spec-kit/firebird-database.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.06358 |
| Opus 5 | $0.00012 | $0.03179 |
| Sonnet 5 | $0.00005 | $0.01272 |
| Haiku 4.5 | $0.00002 | $0.00636 |
Grade A, and why
Firebird Database 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 3d 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 — 864 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Firebird Database — Skill
Use this skill when working with Firebird database in Delphi projects via FireDAC.
When to Use
- When configuring FireDAC connection with Firebird
- When creating tables, generators, stored procedures, triggers, domains and views
- When implementing Repositories with FireDAC + Firebird
- When working with transactions, isolation levels and concurrency
- When planning schema migrations (versioned scripts)
- When optimizing queries and indexes for Firebird
Firebird Versions
| Version | Relevant News |
|---|---|
| 2.5 | Trace API, LIST() aggregate, Windows Trusted Auth |
| 3.0 | Native BOOLEAN, IDENTITY columns, Packages, UDR (replaces UDF), Window Functions (OVER), Encryption |
| 4.0 | DECFLOAT, INT128, TIME/TIMESTAMP WITH TIME ZONE, Replication, Batch API, LATERAL join |
| 5.0 | WHEN NOT MATCHED BY SOURCE, Parallel Backup, SQL Security hardening, Profiler |
Recommendation: Use Firebird 3.0+ for new projects. Avoid deprecated features like UDFs.
FireDAC connection with Firebird
Minimum Configuration
unit MeuApp.Infra.Database.Connection;
interface
uses
FireDAC.Comp.Client,
FireDAC.Phys.FB, //Driver Firebird
FireDAC.Phys.FBDef, //Defaults do Firebird
FireDAC.Stan.Def,
FireDAC.Stan.Pool,
FireDAC.DApt;
type
///<summary>
///Firebird connection factory via FireDAC.
///</summary>
TFirebirdConnectionFactory = class
public
///<summary>
///Creates and configures a Firebird connection.
///</summary>
///<param name="ADatabasePath">Full path of the .fdb file</param>
///<param name="AUserName">User (default: SYSDBA)</param>
///<param name="APassword">Bank password</param>
///<returns>FireDAC connection configured and opened</returns>
class function CreateConnection(
const ADatabasePath: string;
const AUserName: string = 'SYSDBA';
const APassword: string = 'masterkey'
): TFDConnection;
///<summary>
///Creates a connection via Embedded Server (without fbserver).
///</summary>
class function CreateEmbeddedConnection(
const ADatabasePath: string
): TFDConnection;
end;
implementation
uses
System.SysUtils;
class function TFirebirdConnectionFactory.CreateConnection(
const ADatabasePath: string;
const AUserName: string;
const APassword: string): TFDConnection;
begin
if ADatabasePath.Trim.IsEmpty then
raise EArgumentException.Create('ADatabasePath não pode ser vazio');
Result := TFDConnection.Create(nil);
try
Result.DriverName := 'FB';
Result.Params.Database := ADatabasePath;
Result.Params.UserName := AUserName;
Result.Params.Password := APassword;
{ Configurações recomendadas }
Result.Params.Values['CharacterSet'] := 'UTF8';
Result.Params.Values['Protocol'] := 'TCPIP'; // Local: 'Local'
Result.Params.Values['Server'] := 'localhost';
Result.Params.Values['Port'] := '3050';
Result.Params.Values['SQLDialect'] := '3'; //ALWAYS Dialect 3
Result.Params.Values['PageSize'] := '16384'; // 16KB recomendado
{ Opções do driver FireDAC }
Result.FormatOptions.StrsTrim2Len := True; //Trim CHAR for VARCHAR
Result.FetchOptions.Mode := fmAll; // Fetch completo
Result.ResourceOptions.AutoReconnect := True; //Automatic reconnection
Result.TxOptions.Isolation := xiReadCommitted; //Standard isolation
Result.Connected := True;
except
Result.Free;
raise;
end;
end;
class function TFirebirdConnectionFactory.CreateEmbeddedConnection(
const ADatabasePath: string): TFDConnection;
begin
Result := TFDConnection.Create(nil);
try
Result.DriverName := 'FB';
Result.Params.Database := ADatabasePath;
{ Embedded: sem servidor, sem user/password obrigatórios no FB3+ }
Result.Params.Values['Protocol'] := 'Local';
Result.Params.Values['CharacterSet'] := 'UTF8';
Result.Params.Values['SQLDialect'] := '3';
Result.Connected := True;
except
Result.Free;
raise;
end;
end;
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.
- 3d ago First seen · 864 lines · 24 tokens per session scan A 2f51ee08887e
Firebird Database is a skill published in the GitHub repository delphicleancode/delphi-spec-kit (50 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 6,358 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
authentication-patterns
Authentication patterns: session vs JWT vs OAuth comparison, provider selection (NextAuth, Clerk, Supabase Auth), security checklist, and common mistakes. Use when implementing auth, reviewing auth flows, or choosing auth providers.
code-vuln-audit
Scan code for security issues: dependency vulnerabilities (npm/pip audit), secret leaks (regex and entropy analysis), and OWASP anti-patterns like SQL injection, XSS, or command injection. Use when the user mentions security scans, vulnerability detection, secret leaks, API keys, OWASP, npm audit, pip-audit, hardcoded…
database-scout
Explore SQLite and PostgreSQL databases: list tables, inspect schemas (columns/types/constraints), preview data, generate Mermaid ER diagrams, and run safe read-only queries. Triggered by requests to explore a database, view table structures, describe tables, generate diagrams, or query data, and by keywords like…
database-optimizer
Use when investigating slow queries, analyzing execution plans, or optimizing database performance. Invoke for index design, query rewrites, configuration tuning, partitioning strategies, lock contention resolution.
horse-database-pooling
Guide for setting up thread-safe database connection pooling (FireDAC / UniDAC) in multithreaded Horse applications.
data-warehouse-experimentation
Running experiments out of the data warehouse instead of via dedicated experiment platforms. SQL-based assignment, exposure logging discipline, metric definitions in dbt models, statistical analysis in SQL or Python, variance reduction with CUPED, sequential testing, and the operational tradeoffs vs platforms like…