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/copilot-instructionsgit 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 | $0.02899 | $0.02899 |
| Opus 5 | $0.01450 | $0.01450 |
| Sonnet 5 | $0.00580 | $0.00580 |
| Haiku 4.5 | $0.00290 | $0.00290 |
Grade A, and why
delphi-spec-kit copilot-instructions.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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot — Instructions for Delphi Projects
Contexto
This is a Delphi (Object Pascal) project that follows SOLID principles, clean code and the Object Pascal Style Guide. See AGENTS.md in the project root for the complete convention reference.
General Guidelines
- Always generate code in Object Pascal (Delphi) unless explicitly requested in another language.
- Use PascalCase for all identifiers. Lowercase reserved words.
- Respect the prefixes of the Pascal convention:
T(classes),I(interfaces),E(exceptions),F(private fields),A(parameters),L(local variables). - Prefer interfaces over concrete classes for dependencies.
- Use constructor injection for dependency injection.
- Never put business logic in form event handlers (
OnClick,OnChange, etc.). Delegate to services.
Code Style
Indentation and Formatting
- Indentation: 2 spaces (no tabs)
beginon the same line ofif,for,while,withwhen in a single blockbeginon new line for method implementations- Limit of 120 characters per line
Unit Sections
Order unit sections according to:
unit Nome;
interface
uses
{ RTL units },
{ Units do projeto };
type
{ Enums e Records }
{ Interfaces }
{ Classes }
implementation
uses
{ Units adicionais só necessárias na implementação };
{ Implementações }
end.
Variable Declaration
// Preferir inline var quando disponível (Delphi 10.3+)
var LCustomer := TCustomer.Create('João');
// Ou declaraction explícita com prefixo L
var
LCustomer: TCustomer;
LCount: Integer;
Error Handling
- Use specific exceptions (create exception classes per domain):
EBusinessRuleException = class(Exception); EEntityNotFoundException = class(Exception); EValidationException = class(Exception); - Guard clauses at the beginning of the method instead of deep nesting
- Try/finally for memory management
- Try/except only for actual error handling, never for control flow
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 · 214 lines · 2,899 tokens per session scan A 678a3c3f2378
delphi-spec-kit copilot-instructions.md is an instructions file published in the GitHub repository delphicleancode/delphi-spec-kit (50 stars, last pushed 5mo ago), licensed MIT. It adds 2,899 tokens to every session, about $0.0145 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.
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.
claude-sessions CLAUDE.md
Instructions for gapmiss/claude-sessions, covering claude sessions — obsidian plugin, development, file structure, code exploration (cymbal) and conventions.
embedded-systems-architect AGENTS.md
Instructions for Zachariah9420/embedded-systems-architect: This repository ships an agent skill for embedded-systems and edge-AI development work.
contexture AGENTS.md
Instructions for AcKeskin/contexture, covering agents.md, stance (how to engage), commands, testing and project structure.
claude-skill-management-consultant-B1 AGENTS.md
AGENTS.md instructions for DogInfantry/claude-skill-management-consultant-B1: This repository is an MBB-level (McKinsey / Bain / BCG) management-consulting skill: structured problem solving (MECE issue trees, hypothesis-driven analysis), strategy frameworks, market sizing / guesstimation, case-interview structures…