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/secondlifes/delphi-expert/delphi-memory-exceptionsnpx skills add SecondLifes/delphi-expert --skill delphi-memory-exceptionsgit clone --depth 1 https://github.com/SecondLifes/delphi-expertWhat 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 | $0.00019 | $0.01424 |
| Opus 5 | $0.00010 | $0.00712 |
| Sonnet 5 | $0.00004 | $0.00285 |
| Haiku 4.5 | $0.00002 | $0.00142 |
Grade A, and why
delphi-memory-exceptions 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🧠 Memory and Exceptions Management in Delphi
Contexto
Delphi has manual memory management for class instances (not derived from interfaces) and uses ARC (Automatic Reference Counting) only for interfaces (IInterface), Strings, Dynamic Arrays and anonymous types. Poor exception handling and forgetting to release memory result in chronic Memory Leaks, catastrophic production failures and systemic instability.
Like AI, you must proactively ensure that every object you create is freed regardless of error streams.
Objectives of this Skill
- Teach how to generate safe blocks of
try..finally. - Prevent Memory Leaks by advising on
FreeandFreeAndNil. - Promote the use of Interfaces for memory automation.
- Institute defensive and typed handling of Exceptions (
try..except). - Introduce custom Domain Exceptions.
🛑 Memory Management: Critical Rules
1. The Gold Standard: try..finally
Whenever an object instance is created and does not have an Owner who manages it, instantiate it in a try..finally block.
try must occur IMMEDIATELY on the line following creation.
var
LList: TStringList;
begin
LList := TStringList.Create;
try
LList.Add('Item 1');
// ...
finally
LList.Free;
end;
end;
Anti-Pattern (DO NOT USE):
Code between Create and try may generate an exception, leaking the newly created object.
//WRONG - potential leak!
LList := TStringList.Create;
LList.Add('Item 1');
try
// ...
2. Multiple Objects in the Same Block
When allocating multiple temporary resources in the same method, apply this rule of thumb:
- Dependent objects (one wraps/consumes another, e.g.
TStreamReaderreading from aTMemoryStream) → nest onetry..finallyper object, freeing in reverse order of creation:
var
LStream: TMemoryStream;
LReader: TStreamReader;
begin
LStream := TMemoryStream.Create;
try
LReader := TStreamReader.Create(LStream);
try
//logics with both
finally
LReader.Free;
end;
finally
LStream.Free;
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.
- 2d ago First seen · 189 lines · 19 tokens per session scan A 06b9d33bdd34
delphi-memory-exceptions is a skill published in the GitHub repository SecondLifes/delphi-expert (3 stars, last pushed 22d ago), licensed MIT. It adds 19 tokens to every session and 1,424 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.