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 TalissonVitorino/kmp-ios-skills --skill swiftlintgit clone --depth 1 https://github.com/TalissonVitorino/kmp-ios-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/talissonvitorino/kmp-ios-skills/swiftlint)<a href="https://agentmods.dev/skills/talissonvitorino/kmp-ios-skills/swiftlint"><img src="https://agentmods.dev/badge/skills/talissonvitorino/kmp-ios-skills/swiftlint/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/talissonvitorino/kmp-ios-skills/swiftlint"><img src="https://agentmods.dev/badge/skills/talissonvitorino/kmp-ios-skills/swiftlint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00251 | $0.04211 |
| Opus 5.5 | $0.00100 | $0.01684 |
| Sonnet 5.5 | $0.00050 | $0.00842 |
| Haiku 4.5 | $0.00025 | $0.00421 |
Grade A, and why
swiftlint 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 2mo 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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SwiftLint (iOS / Swift)
Static analysis and style enforcement for Swift. This skill covers configuration
authoring, build integration, and rollout — grounded in the realm/SwiftLint
and SimplyDanny/SwiftLintPlugins docs. For a fintech codebase the goal is a lint gate
that blocks new violations without a big-bang cleanup of the existing ones.
- SwiftLint has two rule engines: lint rules (syntactic, AST via SourceKit) run by
swiftlint lint(default), and analyzer rules run byswiftlint analyzeagainst a compiler log. - Ships default-on rules plus a large opt-in set.
swiftlint ruleslists every rule and whether it's enabled;swiftlint reporterslists output formats.
Contents
- Install
- .swiftlint.yml
- Rule severity & thresholds
- Custom rules (regex)
- Inline suppression
- Build integration (SPM plugin / run script)
- Analyzer rules
- Reporters
- strict vs lenient
- Baselines (legacy rollout)
- CI
- Rollout strategy
- Checklist
- References:
references/config-reference.md,references/custom-rules.md,references/ci-recipes.md
Install
Pin the version so every machine and CI runner lints identically — a floating SwiftLint silently changes what fails.
brew install swiftlint # local dev (unversioned; fine for editors)
mint install realm/SwiftLint # Mintfile-pinned
- Preferred for reproducibility: the SPM build-tool plugin (below) — it vendors a pinned binary per package, so no separate install step and no version drift between developers and CI.
- Avoid the CocoaPods
SwiftLintpod on new projects; the SPM plugin supersedes it.
.swiftlint.yml
Place at the repo root (or a target/subdirectory root — SwiftLint walks up from each file and applies the nearest config). Keys:
# --- rule selection ---
disabled_rules: # turn OFF default-on rules
- todo
- trailing_whitespace
opt_in_rules: # turn ON rules that are off by default
- empty_count
- first_where
- force_unwrapping
- explicit_init
- all # special: enable EVERY opt-in rule (minus disabled_rules)
# only_rules: # allow-list: ONLY these run. Mutually exclusive with
# - force_cast # disabled_rules AND opt_in_rules — do not combine.
# - force_try
analyzer_rules: # separate list, run only by `swiftlint analyze` (all opt-in)
- unused_import
- unused_declaration
# --- paths (case-sensitive, relative to the config file) ---
included: # if set, lint ONLY these (still minus `excluded`)
- Sources
excluded: # skip these; wins over `included`
- Tests
- .build
- Pods
- "**/Generated" # generated code (protobuf, Sourcery, R.swift) — never lint
# --- output ---
reporter: "xcode" # default; see Reporters section
# --- global severity ---
strict: false # true → warnings become errors (nonzero exit)
lenient: false # true → errors become warnings (never fails)
What ships with it
3 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.
- 2mo ago First seen · 341 lines · 251 tokens per session scan A 6b03d967e65a
swiftlint is a skill published in the GitHub repository TalissonVitorino/kmp-ios-skills (16 stars, last pushed 2mo ago), licensed MIT. It adds 251 tokens to every session and 4,211 once invoked, about $0.0010 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 2026-09-03.
swiftlint compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| swiftlintTalissonVitorino/kmp-ios-skills | Skill | 16 | 2mo ago | MIT | A | 251 | Claude Code, Codex |
| compose-multiplatformericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 80 | Claude Code, Codex |
| cmp-dev-clientkvdm-co-pilot/create-cmp | Skill | 0 | 16d ago | MIT | A | 139 | Claude Code |
| cmp-previewkvdm-co-pilot/create-cmp | Skill | 0 | 16d ago | MIT | B | 205 | Claude Code |
| kotlin-concurrency-and-flowchrisbanes/skills | Skill | 1.1k | yesterday | Apache-2.0 | A | 60 | Claude Code |
| kotlin-api-designchrisbanes/skills | Skill | 1.1k | yesterday | Apache-2.0 | A | 46 | Claude Code |
| android-coroutines-prokelvinkosbab/AppBootstrapAI | Skill | 8 | today | MIT | A | 56 | Claude Code |