Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/charlesjones-dev/claude-code-plugins-devnpx agentmods add skills/charlesjones-dev/claude-code-plugins-dev/swift-ci-scaffoldWrote 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/charlesjones-dev/claude-code-plugins-dev/swift-ci-scaffold)<a href="https://agentmods.dev/skills/charlesjones-dev/claude-code-plugins-dev/swift-ci-scaffold"><img src="https://agentmods.dev/badge/skills/charlesjones-dev/claude-code-plugins-dev/swift-ci-scaffold/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/charlesjones-dev/claude-code-plugins-dev/swift-ci-scaffold"><img src="https://agentmods.dev/badge/skills/charlesjones-dev/claude-code-plugins-dev/swift-ci-scaffold.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Privilege Escalation · line 117 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00082 | $0.01798 |
| Opus 5.5 | $0.00033 | $0.00719 |
| Sonnet 5.5 | $0.00016 | $0.00360 |
| Haiku 4.5 | $0.00008 | $0.00180 |
Grade A, and why
swift-ci-scaffold 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swift CI Scaffolder
You prepare the repo side of Xcode Cloud for a generator-based Swift project, and you fix the two build-system blockers that /swift-preflight flags: a missing/weak ci_post_clone.sh and a static build number. You also optionally install a local pre-push gate.
You cannot create or edit the Xcode Cloud workflow itself - those live in App Store Connect, not the repo. You scaffold what the repo can hold and print the exact UI steps for the rest.
Rules
- Non-destructive. Probe first, propose a diff, confirm, then write. Never overwrite an existing
ci_post_clone.sh,project.yml, or hook without showing the change and getting a yes. - Preserve the source of truth. On XcodeGen, edits go into
project.yml, never the pbxproj. Read the real deployed bundle id / team from the pbxproj first and make sureproject.ymlalready carries them (if not, tell the user to reconcile - see/swift-preflightCheck 1 - before you scaffold a regen step, because regen would otherwise revert their signing identity). - Idempotent. If a well-formed script/scheme/hook already exists, say so and offer to only patch the missing pieces.
Arguments
$ARGUMENTS: optional path (repo root, default cwd); --hook jumps straight to the pre-push hook step.
Phase 0: Probe
Detect the generator (xcodegen / tuist), platforms, existing ci_scripts/, the app + unit-test + UI-test targets, and the current CURRENT_PROJECT_VERSION. If the project is a plain .xcodeproj (no generator) or SwiftPM library, tell the user this scaffolder is for generator-based app projects on Xcode Cloud and stop (offer /swift-verify instead).
Critical pre-check (XcodeGen drift): before proposing a regen-on-CI script, confirm project.yml already declares the real PRODUCT_BUNDLE_IDENTIFIER and DEVELOPMENT_TEAM that the pbxproj uses:
grep -E 'PRODUCT_BUNDLE_IDENTIFIER|DEVELOPMENT_TEAM' *.xcodeproj/project.pbxproj | sort -u
If project.yml is missing either, stop and warn: adding a CI regen step now would revert the hand-set signing identity and break the App Store record. Have the user copy the real values into project.yml settings.base first.
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 · 137 lines · 82 tokens per session scan A 0f3fb8342f48
swift-ci-scaffold is a skill published in the GitHub repository charlesjones-dev/claude-code-plugins-dev (35 stars, last pushed 13d ago), licensed MIT. It adds 82 tokens to every session and 1,798 once invoked, about $0.0003 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 2026-09-06.
Other skills, from other repositories
release-kotlin-library
Use when preparing, publishing, or checking readiness for a Kotlin library release, including verifying its gradle-maven-publish-plugin prerequisite, reconciling changelogs and API snapshots, and checking publication.
dart-package-maintenance
Guidelines for maintaining external Dart packages, covering versioning, publishing workflows, and pull request management. Use when updating Dart packages, preparing for a release, or managing collaborative changes in a repository.
xcode-build-tuner
Implement approved Xcode build-speed fixes after strategist approval or explicit requests covering build settings, script phases, Swift compilation, or SwiftPM graphs; re-benchmark results.
gradle-build-expert
Expert en configuration et optimisation Gradle pour Android Kotlin. Gère build.gradle, Kotlin DSL, dépendances, flavours, variants, performance, CI/CD et troubleshooting avancé. Se déclenche avec "gradle", "build error", "dépendance", "build config". Also triggers on "Gradle build", "Kotlin DSL build script", "speed…
kmp-library-publishing
Publish a Kotlin Multiplatform library to Maven Central, GitHub Packages, or both. Covers: vanniktech maven-publish plugin setup, POM metadata, Sonatype OSSRH staging, multi-artifact BOM, kotlinx-binary-compatibility-validator API tracking, SNAPSHOT vs stable channels, and a release checklist. Pairs with…
kmp-ci-github-actions
Sets up GitHub Actions CI for a Kotlin Multiplatform (KMP) project. Produces two workflow files: ci.yml (lint, Android tests, iOS tests, Desktop JVM tests, Web JS + WasmJs tests, Gradle cache) and release.yml (XCFramework build + upload artifact). All target platforms are covered. Assumes AGP 9+ and the project…