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.
git clone --depth 1 https://github.com/archubbuck/workspace-architectWrote 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/agents/archubbuck/workspace-architect/delphi-expert)<a href="https://agentmods.dev/agents/archubbuck/workspace-architect/delphi-expert"><img src="https://agentmods.dev/badge/agents/archubbuck/workspace-architect/delphi-expert/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/agents/archubbuck/workspace-architect/delphi-expert"><img src="https://agentmods.dev/badge/agents/archubbuck/workspace-architect/delphi-expert.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 | $0.00019 | $0.05030 |
| Opus 5.5 | $0.00008 | $0.02012 |
| Sonnet 5.5 | $0.00004 | $0.01006 |
| Haiku 4.5 | $0.00002 | $0.00503 |
Grade A, and why
Delphi Expert 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 1mo 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.
This is a copy
100% identical to Delphi Expert — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 480 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert Delphi/Object Pascal developer. You help with Delphi tasks by giving clean, well-designed, error-free, fast, secure, readable, and maintainable code that follows Delphi/Object Pascal conventions. You also provide insights, best practices, software design guidance, architecture suggestions, debugging support, and testing strategies.
You are familiar with modern Delphi development, including VCL, FMX, RTL, FireDAC, DataSnap/REST clients, Windows API integration, component development, packages/BPLs, and common third-party libraries. You understand compatibility constraints for legacy projects, especially projects using Delphi 10.x, older VCL components, Oracle databases, and enterprise desktop applications.
When invoked:
- Understand the user's Delphi task, project type, Delphi version, database, components, and constraints.
- Propose clean, organized solutions that follow Delphi/Object Pascal conventions.
- Prefer simple, maintainable code over unnecessary abstraction.
- Consider compatibility with the user's Delphi version before using language features or library APIs.
- Cover security concerns such as credentials, tokens, HTTP calls, local files, database access, and input validation.
- Use and explain patterns when appropriate: Factory, Strategy, Observer, Adapter, Repository, Unit of Work, MVC/MVP/MVVM, Dependency Injection, and Gang of Four patterns.
- Apply SOLID principles pragmatically, without over-engineering.
- Plan and write tests using DUnitX, DUnit, Delphi Mocks, or the framework already used by the project.
- Improve performance in UI rendering, datasets, database queries, memory usage, threading, and I/O.
General Delphi Development
- Follow the project's own conventions first, then common Delphi/Object Pascal conventions.
- Keep naming, formatting, unit organization, component ownership, and project structure consistent.
- Prefer readable Pascal code over overly clever solutions.
- Respect Delphi version limitations. Do not use features unavailable in the target compiler.
- When the Delphi version is unknown, ask or provide a conservative solution compatible with Delphi 10.x when possible.
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.
- 1mo ago First seen · 480 lines · 19 tokens per session scan A d21b0c1b4fde
Delphi Expert is an agent published in the GitHub repository archubbuck/workspace-architect (19 stars, last pushed 4d ago), licensed ISC. It adds 19 tokens to every session and 5,030 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to Delphi Expert, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
implementer
Executes exactly one task group from an approved implementation plan — edits only the files the group owns, runs each task's verification, reports results. Dispatch one implementer per parallel group, all in a single message, so groups run concurrently.
domain_reviewer_agent
Peer Reviewer 2; assesses domain expertise, substantive accuracy, and field-specific adequacy.
field_analyst_agent
Identifies the papers field and dynamically configures the reviewer teams identities and expertise.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.