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 Prisma-Labs-Dev/apple-skills --skill guide-swiftdatagit clone --depth 1 https://github.com/Prisma-Labs-Dev/apple-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/prisma-labs-dev/apple-skills/guide-swiftdata)<a href="https://agentmods.dev/skills/prisma-labs-dev/apple-skills/guide-swiftdata"><img src="https://agentmods.dev/badge/skills/prisma-labs-dev/apple-skills/guide-swiftdata/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/prisma-labs-dev/apple-skills/guide-swiftdata"><img src="https://agentmods.dev/badge/skills/prisma-labs-dev/apple-skills/guide-swiftdata.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 20 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00038 | $0.00476 |
| Opus 5.5 | $0.00015 | $0.00190 |
| Sonnet 5.5 | $0.00008 | $0.00095 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
guide-swiftdata 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.
What it actually says
Guide Skill — This is an expert workflow/pattern guide, not API reference documentation. Originally from twostraws/SwiftData-Agent-Skill by Paul Hudson. MIT License.
SwiftData Patterns
Write and review SwiftData code for correctness, modern API usage, and adherence to project conventions. Report only genuine problems — do not nitpick or invent issues.
Core Instructions
- Target Swift 6.2 or later, using modern Swift concurrency.
- Prefer SwiftData across the board. Do not suggest Core Data unless the feature cannot be solved with SwiftData.
- Do not introduce third-party frameworks without asking first.
Review Process
- Check for core SwiftData issues using
references/core-rules.md. - Check that predicates are safe and supported using
references/predicates.md. - If the project uses CloudKit, check for CloudKit-specific constraints using
references/cloudkit.md. - If the project targets iOS 18+, check for indexing opportunities using
references/indexing.md. - If the project targets iOS 26+, check for class inheritance patterns using
references/class-inheritance.md.
If doing partial work, load only the relevant reference files.
References
| Topic | Reference |
|---|---|
Autosave, relationships, delete rules, @Query restrictions, #Unique, @Transient |
references/core-rules.md |
| Supported predicates, dangerous patterns that crash at runtime, unsupported methods | references/predicates.md |
CloudKit constraints: no #Unique, optional requirements, eventual consistency |
references/cloudkit.md |
| Database indexing (iOS 18+), single and compound property indexes | references/indexing.md |
Model subclassing (iOS 26+), @available requirements, predicate filtering |
references/class-inheritance.md |
What ships with it
5 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.
- 1mo ago First seen · 41 lines · 38 tokens per session scan A 517426661483
guide-swiftdata is a skill published in the GitHub repository Prisma-Labs-Dev/apple-skills (347 stars, last pushed 26d ago), licensed MIT. It adds 38 tokens to every session and 476 once invoked, about $0.0002 per session on Opus 5.5. 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
kotlin-exposed-patterns
JetBrains Exposed ORM patterns including DSL queries, DAO pattern, transactions, HikariCP connection pooling, Flyway migrations, and repository pattern.
cratis-arc-spring-data-kotlin
Use Spring Data JPA or MongoDB with Kotlin or Java Arc read models — repository-backed queries and paging, command current-state resolution, observable snapshots, concept converters, certified tenant storage and explicit transaction opt-ins. Use when wiring JVM Arc persistence or database-backed observations. Do not…
jpa-spring-data-kotlin-mapper
Model Kotlin persistence code correctly for Spring Data JPA and Hibernate, including entity design, relationships, fetch plans, repository queries, lazy loading, and common performance traps. Use when creating or reviewing entities and repositories, diagnosing N+1 or LazyInitializationException, placing indexes and…
kotlin-backend-jpa-entity-mapping
Model Kotlin persistence code correctly for Spring Data JPA and Hibernate. Covers entity design, identity and equality, uniqueness constraints, relationships, fetch plans, and common ORM (Object-Relational Mapping) traps specific to Kotlin. Use when creating or reviewing JPA (Java Persistence API) entities, diagnosing…
bmob-database-swift
Use when implementing Bmob NoSQL database CRUD or realtime data listening with the pure Swift BmobSwiftSDK for iOS 15+ / macOS 12+ using Swift Package Manager or CocoaPods, import BmobSDK, async/await, Bmob.initialize(appKey:), BmobObject, BmobQuery, BmobUser, BmobFile, BmobPointer, BmobRelation, BmobGeoPoint…
postgres-nio
Expert guidance on using PostgreSQL with Swift. Use when developers mention: (1) PostgreSQL or Postgres in Swift, (2) postgres-nio library, (3) SQL queries in Swift, (4) PostgreSQL connection pooling, (5) prepared statements, (6) type-safe database access, (7) bulk loading or COPY FROM, (8) PostgresClient or…