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 instructions/delphicleancode/delphi-spec-kit/agents-mdgit clone --depth 1 https://github.com/delphicleancode/delphi-spec-kitWhat 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 | $0.06709 | $0.06709 |
| Opus 5 | $0.03354 | $0.03354 |
| Sonnet 5 | $0.01342 | $0.01342 |
| Haiku 4.5 | $0.00671 | $0.00671 |
Grade A, and why
delphi-spec-kit AGENTS.md 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 2d 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 — 726 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delphi AI Spec-Kit — AGENTS.md
This file is automatically recognized by Antigravity, GitHub Copilot, Cursor and Kiro. It defines the universal rules for Delphi development with AI.
Language and Stack
- Language: Object Pascal (Delphi)
- Native IDE: RAD Studio / Delphi
- Frameworks: VCL, FMX, FireDAC
- Database: FireDAC (SQLite, PostgreSQL, Firebird, SQL Server)
- Tests: DUnitX
- Build: MSBuild / Delphi Compiler (dcc32/dcc64)
- File extensions:
.pas(units),.dfm/.fmx(forms),.dpr(project),.dpk(package),.dproj(project config)
Naming Conventions — Pascal Guide
General Rule
Use PascalCase (InfixCaps) for all identifiers. Reserved words are always in **TOK_6__, end, if, then, else, nil, string).
Mandatory Prefixes
| Type | Prefix | Example |
|---|---|---|
| Class | T |
TCustomerRepository |
| Interface | I |
ICustomerRepository |
| Exception | E |
ECustomerNotFound |
| Private field | F |
FCustomerName |
| Parameter | A |
ACustomerName |
| Enumerated type | T |
TOrderStatus |
| Enum Items | short prefix | osNew, osPending, osClosed |
Unit Naming
NomeProjeto.Camada.Dominio.Funcionalidade.pas
Examples:
MyApp.Domain.Customer.Entity.pasMyApp.Infra.Customer.Repository.pasMyApp.Application.Customer.Service.pasMyApp.Presentation.Customer.View.pas
Method Naming
- Action methods: use verbs —
Execute,CreateOrder,ValidateCustomer - Getters: prefix
Get—GetCustomerName - Setters: prefix
Set—SetCustomerName - Boolean functions: prefix
Is,Has,Can—IsValid,HasPermission,CanDelete
Unit Test Naming (TDD)
- Follow the generic behavioral pattern in DUnitX tests:
Action_Condition_ExpectedResult - Example:
ProcessOrder_WithoutStock_RaisesException,CalculateTotal_WithDiscount_ReturnsLowerValue - Create fakes in the test unit with prefix
TFake(ex:TFakeInventoryRepository)
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.
- 2d ago First seen · 726 lines · 6,709 tokens per session scan A 6182580fa18d
delphi-spec-kit AGENTS.md is an instructions file published in the GitHub repository delphicleancode/delphi-spec-kit (50 stars, last pushed 5mo ago), licensed MIT. It adds 6,709 tokens to every session, about $0.0335 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 instructions, from other repositories
delphi-ai-skills CLAUDE.md
Instructions for danieleteti/delphi-ai-skills, covering claude.md, what this repository is, the iron rule, layout and hard constraints on a skill.md.
mcp-server-excel coverage-prevention-strategy.instructions.md
Instructions for sbroenne/mcp-server-excel, covering generated surface coverage, contract change workflow, required checks and common incomplete changes.
my-claude-code-setup GEMINI.md
Instructions for centminmod/my-claude-code-setup, covering gemini.md, ai guidance, memory bank system, core context files and project overview.
mcp-server-excel mcp-llm-guidance.instructions.md
Instructions for sbroenne/mcp-server-excel, a project described as: Automate real Microsoft Excel with AI via MCP Server or CLI — Power Query, DAX, VBA, PivotTables, charts, and 326 operations.
cship CLAUDE.md
Instructions for stephenleo/cship, covering cship — ai agent instructions, environment quirks, non-negotiable code patterns, before submitting a pr and project structure.
agentic-workflow CLAUDE.md
Instructions for gtrabanco/agentic-workflow, covering claude.md, repository layout, working rules, authoring a skill and hand off, don't compose across a model/effort boundary.