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 laxrajpurohit/swift-skills-pro --skill swift-guardrails-progit clone --depth 1 https://github.com/laxrajpurohit/swift-skills-proWrote 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/laxrajpurohit/swift-skills-pro/swift-guardrails-pro)<a href="https://agentmods.dev/skills/laxrajpurohit/swift-skills-pro/swift-guardrails-pro"><img src="https://agentmods.dev/badge/skills/laxrajpurohit/swift-skills-pro/swift-guardrails-pro/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/laxrajpurohit/swift-skills-pro/swift-guardrails-pro"><img src="https://agentmods.dev/badge/skills/laxrajpurohit/swift-skills-pro/swift-guardrails-pro.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00079 | $0.01940 |
| Opus 5.5 | $0.00032 | $0.00776 |
| Sonnet 5.5 | $0.00016 | $0.00388 |
| Haiku 4.5 | $0.00008 | $0.00194 |
Grade B, and why
swift-guardrails-pro scanned grade B with 3 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 9d 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.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| `<skill>/scripts/pbxproj-scan.sh` | grep | build-phase injection in `project.pbxproj` (base64/xxd decode, `curl \| sh`, hidden background jobs, `osascript`) | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| `npx swift-skills-cli install` | `~/.claude/settings.json`, `~/.cursor/hooks.json`, `~/.codex/hooks.json`, `~/.codeium/windsurf/hooks.json` (each agent found on the machine) | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `<skill>/scripts/pbxproj-scan.sh` | grep | build-phase injection in `project.pbxproj` (base64/xxd decode, `curl \| sh`, hidden background jobs, `osascript`) | How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swift Guardrails Pro
Coding rules that run on their own instead of advice someone has to remember. Everything is a ratchet: only lines a change adds or modifies are checked, so a legacy codebase adopts it on day one with no cleanup sprint.
No setup. Nothing is copied into the project. The scripts sit next to this
file in scripts/ and work out the source folders, base branch, and lint config
on their own. Installing the skill also wires them into the agent's hooks, so
they run automatically:
| When | What runs | Effect |
|---|---|---|
After the agent edits a .swift file |
lint + copy-paste on that file's changed lines | findings go back to the agent to fix |
Before the agent runs git commit |
pbxproj scan + lint + copy-paste on staged lines | commit blocked until fixed |
| Installed via | Hooks registered in |
|---|---|
| Claude Code plugin | the plugin itself |
npx swift-skills-cli install |
~/.claude/settings.json, ~/.cursor/hooks.json, ~/.codex/hooks.json, ~/.codeium/windsurf/hooks.json (each agent found on the machine) |
| Manual copy | none yet; see "Registering hooks by hand" |
When to use
- "Check my changes", "lint this branch", "any copy-paste in this PR?"
- "Stop copy-pasted views", "make sure nobody duplicates code".
- Adding a project-specific rule (design tokens, banned APIs).
- Enabling the checks for commits made outside Claude Code.
Trigger: /swift-guardrails-pro or natural language.
The checks
<skill> below is this file's directory. Run from anywhere inside the repo.
| Script | Tool | Fails on |
|---|---|---|
<skill>/scripts/lint-changed.sh |
SwiftLint | error violations on changed lines (after an edit, warnings too, so the agent fixes them; a commit is blocked by errors only) |
<skill>/scripts/dup-check.sh |
jscpd | a duplicated block (≥ 8 lines / 60 tokens) that is at least half new |
<skill>/scripts/pbxproj-scan.sh |
grep | build-phase injection in project.pbxproj (base64/xxd decode, curl | sh, hidden background jobs, osascript) |
What ships with it
9 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.
- scripts/_common.sh 3.9 KB runs code
- scripts/_filter.py 4.4 KB runs code
- scripts/agent-hook.sh 4.1 KB runs code
- scripts/dup-check.sh 2.4 KB runs code
- scripts/install-hooks.sh 1.8 KB runs code
- scripts/lint-changed.sh 2.8 KB runs code
- scripts/pbxproj-scan.sh 2.3 KB runs code
- scripts/pre-commit 788 B
- templates/swiftlint.yml 3.6 KB
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.
- 9d ago First seen · 152 lines · 79 tokens per session scan B 2a451a356d20
swift-guardrails-pro is a skill published in the GitHub repository laxrajpurohit/swift-skills-pro (6 stars, last pushed 4d ago), licensed MIT. It adds 79 tokens to every session and 1,940 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-14.
Other skills, from other repositories
coding-best-practices
Reviews Swift/iOS code for adherence to modern Swift idioms, Apple platform best practices, architecture patterns, and code quality standards. Use when user mentions best practices, code review, clean code, refactoring, or wants to improve code quality.
release-review
Senior developer-level release review for macOS/iOS apps. Identifies security, privacy, UX, and distribution issues with actionable fixes. Use when preparing an app for release, want a critical review, or before App Store submission.
tuicr
Use tuicr's review CLI to read and add comments in active TUI review sessions, and launch tuicr in cmux, tmux, Zellij, or Herdr when a user needs an interactive review pane.
liveagent-code-review
Review an open GitHub pull request or the current local branch and working tree with parallel, independent reviewers and evidence-based validation. Use when the user asks for code review, invokes the Code Review action from Git Review, or explicitly mentions this skill.
omh-image-cards
This is an OMH img-summary workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).