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 rules/secondlifes/delphi-expert/memory-exceptionsgit clone --depth 1 https://github.com/SecondLifes/delphi-expertWrote 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/rules/secondlifes/delphi-expert/memory-exceptions)<a href="https://agentmods.dev/rules/secondlifes/delphi-expert/memory-exceptions"><img src="https://agentmods.dev/badge/rules/secondlifes/delphi-expert/memory-exceptions.svg" alt="Measured on agentmods" 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 | $0.00347 | $0.00347 |
| Opus 5 | $0.00173 | $0.00173 |
| Sonnet 5 | $0.00069 | $0.00069 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
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 today.
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.
What it actually says
Memory Rules and Exceptions (Delphi)
- Always use
try..finallyas soon as you instantiate an object (.Create), placing.FreeorFreeAndNil()infinally. The opening oftrymust be IMMEDIATELY on the next line of creation. - DO NOT create multiple objects outside of a safe block. If you have dependencies between them, nest the
try..finallyblocks. Instantiated,tryin the bottom line. - Prefer Interfaces (IInterface) whenever building injectable Services and Repository classes to benefit from the compiler's Reference Count Management (ARC), reducing pollution and eliminating the risk of instantiating without
Freecalls. - DO NOT "Shut" Exceptions: When implementing
try..exceptblocks, always define the exact type of error to be handled (Ex:on E: EFDDBEngineException do). DO NOT use generic blind exceptions or brutal suppression (try ... except ... end) unless explicitly required and with extensive documentation/justification. - DDD Exceptions: For business logic failures, throw custom Exceptions that inherit from
Exception(Ex:raise EBusinessRuleException.Create('Idade inválida para essa operação');). - Safe Relaunch: Use the pure word
raise;when you want to replay the stacktrace forward in aexcept. Standard: Infra processing, capture/intercept/log and pureraise;.
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.
- today First seen · 14 lines · 347 tokens per session scan A aaf1c48c4dda
memory-exceptions is a cursor rule published in the GitHub repository SecondLifes/delphi-expert (3 stars, last pushed 2d ago), licensed MIT. It adds 347 tokens to every session, about $0.0017 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 2026-09-03.
Other cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
memsprout
Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.