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 skills add danieleteti/delphi-ai-skills --skill delphi-code-smellsgit clone --depth 1 https://github.com/danieleteti/delphi-ai-skillsWrote 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/danieleteti/delphi-ai-skills/delphi-code-smells)<a href="https://agentmods.dev/skills/danieleteti/delphi-ai-skills/delphi-code-smells"><img src="https://agentmods.dev/badge/skills/danieleteti/delphi-ai-skills/delphi-code-smells/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/danieleteti/delphi-ai-skills/delphi-code-smells"><img src="https://agentmods.dev/badge/skills/danieleteti/delphi-ai-skills/delphi-code-smells.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 | $0.00167 | $0.01719 |
| Opus 5 | $0.00084 | $0.00860 |
| Sonnet 5 | $0.00033 | $0.00344 |
| Haiku 4.5 | $0.00017 | $0.00172 |
Grade A, and why
delphi-code-smells 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Delphi code smells — make the machine find them first
A review pass that starts with an opinion is worth little. A review pass that starts with the compiler and a leak report is worth a lot, because it is objective and free. Do that half first, every time.
Every warning code, directive and API below was produced by dcc32.exe 37.0 on this machine or copied
from the shipped RTL/DUnitX source, not recalled. Where something could not be verified it says so.
What this skill owns, and what it does not
| Question | Where it is answered |
|---|---|
Why does this leak? How does ownership work? Free, try/finally, interfaces, refcounting, TObjectList<T>, TComponent, managed records |
delphi, reference/memory.md — not restated here |
What is the right try/except shape? What must I never catch? |
delphi, reference/exceptions.md |
Synchronize vs Queue, locks, FreeOnTerminate |
delphi, reference/concurrency.md |
Who frees the object a DMVC action returns? What is ToFree? |
dmvcframework SKILL.md — not restated here |
| How do I find the leak? How do I prove it? How do I stop it coming back? | here |
This skill is diagnosis. When a smell needs semantics to explain, it links; it does not re-teach.
Order of attack — an unfamiliar unit
Work down this list. Stop reporting when you run out of items that cost the user something.
- Compile it with warnings and hints on and read every line of output. Free, objective, and the single
highest-yield step.
reference/static-analysis.md. - Run it with
ReportMemoryLeaksOnShutdown := True. If there is a test suite, run that.reference/leaks.md. - Ownership by hand — every
Createin the unit: who frees it, on which paths, including the raising one. This is where the compiler cannot help you. - Exception handling — every
exceptwithout anon, every empty handler, everytry/exceptthat should have beentry/finally. - Concurrency — anything reachable from a
TThread.Executeor aTTask.Runbody. - Everything else. Naming,
with, long methods, magic numbers.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 112 lines · 167 tokens per session scan A 4344af36c84a
delphi-code-smells is a skill published in the GitHub repository danieleteti/delphi-ai-skills (18 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 167 tokens to every session and 1,719 once invoked, about $0.0008 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
6_gofer_validate
Validate implementation with 10-category engineering rubric (100 points).
Delphi Code Refactoring
Refactoring techniques for Object Pascal focused on improving readability, removing code smells, and preserving behavior through practices like Extract Method, Guard Clauses, and polymorphism.
Delphi Code Review
Delphi code review checklist — quality, security, performance, SOLID, memory.
chinese-code-review
Chinese-language guidance for giving professional, tactful code-review feedback while still calling out real problems.
receiving-code-review
A method for evaluating code-review feedback against the actual code before making changes.
requesting-code-review
A workflow for requesting a review of completed development work before continuing or merging it.