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/aurelius-objectsnpx skills add SecondLifes/delphi-expert --skill aurelius-objectsgit 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 | $0.00155 | $0.01281 |
| Opus 5 | $0.00077 | $0.00641 |
| Sonnet 5 | $0.00031 | $0.00256 |
| Haiku 4.5 | $0.00015 | $0.00128 |
Grade A, and why
aurelius-objects 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Approach
Always work through a TObjectManager instance. All persistence methods (Save, Flush, Remove, etc.) are called on the manager, never written as raw SQL.
Loading a known id: use Manager.Find<T>(Id) — returns the cached instance if already loaded, otherwise hits the database.
Loading multiple objects with criteria: use Manager.Find<T> (no argument) to get a fluent query builder, then call .List.
Saving a new object: call Manager.Save(obj) — the manager takes ownership and tracks changes from that point. Save executes the INSERT immediately. Do not call Flush after Save for a new object; that is only for persisting changes to already-managed objects.
Updating a managed object: just change its properties and call Manager.Flush (or Manager.Flush(obj) for a single object). No explicit "update" call needed.
Updating a transient object (from outside the manager): call Manager.Update(obj) — but be aware this writes all properties on flush, not just the changed ones.
Conflicting identity: if an object with the same id is already cached, use Manager.Merge<T>(transient) instead of Update — it copies data into the existing managed instance.
Deleting: call Manager.Remove(obj) — the object must be managed (loaded through this manager or registered via Save/Update).
Critical Rules
Object lifetime
- Managed entities are owned by the manager and destroyed when it is destroyed — do not free them manually.
- When a query returns a list (
TList<T>), free the list but not the items inside it — the items remain managed. - Projection queries (
ListValues) return lists withOwnsObjects = True; destroying the list also destroys the items. - If you need entities to survive after the manager is freed, set
Manager.OwnsObjects := Falsebefore callingFree. - Call
Manager.AddOwnership(obj)beforeSaveif you want the manager to own the object even whenSaveraises an exception.
What ships with it
1 file 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.
- 2d ago First seen · 74 lines · 155 tokens per session scan A 1f0f15b25afd
aurelius-objects is a skill published in the GitHub repository SecondLifes/delphi-expert (3 stars, last pushed 22d ago), licensed MIT. It adds 155 tokens to every session and 1,281 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…