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.
git clone --depth 1 https://github.com/jeremieb/swift-unit-test-instructionsWrote 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/commands/jeremieb/swift-unit-test-instructions/swift-feature)<a href="https://agentmods.dev/commands/jeremieb/swift-unit-test-instructions/swift-feature"><img src="https://agentmods.dev/badge/commands/jeremieb/swift-unit-test-instructions/swift-feature.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 5.1 | $0.00000 | $0.00557 |
| Opus 5 | $0.00000 | $0.00279 |
| Sonnet 5 | $0.00000 | $0.00111 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
swift-feature 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 8d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement a new Swift feature end-to-end: analysis, confirmation, implementation, and build validation.
Usage
/swift-feature [description of the feature]
Example: /swift-feature user profile screen that displays name, avatar, and a logout button
Phase 1 — Analysis
Before writing a single line of code:
- Read the existing folder structure to understand where the feature belongs
- Identify which files need to be created vs modified
- Check if any required services or protocols already exist
- Determine: does this need a new ViewModel? A new Service? A persistence change?
Present a concise plan:
Feature: [name]
New files:
- Features/[Name]/[Name]View.swift
- Features/[Name]/[Name]ViewModel.swift
Modified files:
- App/ContentView.swift (add navigation entry)
Dependencies needed:
- [Service] — already exists / needs to be created
STOP. Wait for user confirmation before proceeding.
Phase 2 — Implementation
Apply the confirmed plan:
- Follow MVVM strictly: thin View, logic in ViewModel, data access in Service
- Inject all dependencies via
init - Handle loading state, error state, and empty state
- Add
#Previewthat compiles with mock or default data - Use
async/await— no completion handlers - Consult the matching skill for detailed patterns:
- UI →
swift-swiftui-componentorswift-uikit-componentskill - Networking →
swift-networkingskill - Persistence →
swift-persistenceskill
- UI →
Phase 3 — Build Validation
Run /swift-build to confirm the project compiles.
- On success: proceed to Phase 4
- On failure: fix errors (max 2 attempts), then re-run
- If still failing after 2 attempts: stop and present errors to user
Phase 4 — Test Check
Check if the new ViewModel or Service has tests:
- If yes: run tests for the affected target
- If no: flag it — "No tests found for [FeatureName]ViewModel. Use the
swift-testingskill to add them."
Do not write tests automatically — keep this command focused on the feature implementation.
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.
- 8d ago First seen · 86 lines · 0 tokens per session scan A b0651f45fb81
swift-feature is a command published in the GitHub repository jeremieb/swift-unit-test-instructions (5 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 557 tokens. 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 commands, from other repositories
ask
Ask a question about iOS/Swift development - routes to the right Axiom skill or agent.
create-activity
Generate a Jetpack Compose screen with proper architecture.
swift-new
Create new Swift project or component.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.