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/mathisk2095/jko-claude-pluginsWrote 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/mathisk2095/jko-claude-plugins/swift-critique)<a href="https://agentmods.dev/commands/mathisk2095/jko-claude-plugins/swift-critique"><img src="https://agentmods.dev/badge/commands/mathisk2095/jko-claude-plugins/swift-critique.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 | $0.00017 | $0.01245 |
| Opus 5 | $0.00009 | $0.00622 |
| Sonnet 5 | $0.00003 | $0.00249 |
| Haiku 4.5 | $0.00002 | $0.00125 |
Grade A, and why
swift-critique 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 6d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SwiftUI Critique
Load the swiftui-expert skill for reference knowledge, then perform a grounded critique of SwiftUI code.
Gather Context First
Before flagging anything, understand the project:
- Check deployment target from
Package.swift,*.xcodeproj/project.pbxproj, or*.xcconfigfiles - Check if the project uses
@ObservableorObservableObject(don't flagObservableObjectif the whole project consistently uses it and targets < iOS 17) - Check if the project has a design system / theme (shared colors, fonts, spacing constants)
- Note any architectural patterns already in use (MVVM, MV, coordinator, etc.)
What to Critique
If $ARGUMENTS specifies a file or directory, critique that. If no arguments, find Swift files in the current project:
- Use Glob to find
**/*.swiftfiles - Use Read to examine each SwiftUI file (files importing SwiftUI or containing
Viewconformances) - Skip non-SwiftUI files (pure model/utility code without UI)
Critique Rules
- Read the actual code before flagging. Do not flag something you haven't verified by reading the file.
- Respect project conventions. If the project consistently uses a pattern (e.g.,
ObservableObject, computed view properties), don't flag every instance — note it once as a project-wide suggestion. - Verify before flagging. If you think something is unused or misused, check the call sites. An
@Environmentproperty added in the same session may be used in code you haven't read yet. - No generic advice. Every finding must reference a specific file and line number with actual code from the project.
Critique Process
Review each file against these categories in order:
1. Deprecated API
- Flag any deprecated API usage (foregroundColor, NavigationView, ObservableObject, etc.)
- Show the modern replacement with before/after code
2. State & Data Flow
- Verify
@Stateisprivate(skip if the project has a pattern of non-private@Statefor parent injection) - Check
@Observableclasses are@MainActor(only if project targets iOS 17+) - Flag
Binding(get:set:)in body - Flag
@AppStorageinside@Observable - Check for broad observation dependencies (verify by reading the model, not guessing)
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.
- 6d ago First seen · 125 lines · 17 tokens per session scan A ba0061a1def8
swift-critique is a command published in the GitHub repository mathisk2095/jko-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 1,245 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 commands, from other repositories
doctor
Health check for greatcto. Shows pipeline state, missing artefacts, hook status, last run per agent, and permission-denied tail.
review
12-angle code review + skeptical triage (3-round + arbiter) for security/reliability P0/P1 findings, OR traceability tree. Default: review current branch vs main. --deep: triage ALL P0/P1 angles (not just security). With trace : render REQ → IMPL → TEST tree for impact analysis. Creates or closes gate:code for…
release
Release manager for frontend and mobile. Writes App Store notes, user-facing changelog, flags stale docs and landing copy. Actions: notes | changelog | docs | sync.
resume
Resume a previous session. Reads recent session logs, open tasks, and last decisions — gives Claude full context without re-explaining the project.
ccr
CCR (Compressed Context with Retrieval) — recall the full original of context that greatcto compressed/filtered out, by its short id. The retrieval half of the compression layer.
coding-audit
Medical-coding / revenue-cycle compliance audit. Invokes rcm-reviewer to assess autonomous ICD-10-CM / CPT / HCPCS coding for False Claims Act exposure (upcoding/unbundling), NCCI edits + MUEs, medical necessity (LCD/NCD), modifier discipline, HIPAA minimum-necessary — and force a certified-coder (CPC/CCS) sign-off.