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 agentmods add skills/gaelic-ghost/socket/swift-package-extension-workflownpx skills add gaelic-ghost/socket --skill swift-package-extension-workflowgit clone --depth 1 https://github.com/gaelic-ghost/socketWrote 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/gaelic-ghost/socket/swift-package-extension-workflow)<a href="https://agentmods.dev/skills/gaelic-ghost/socket/swift-package-extension-workflow"><img src="https://agentmods.dev/badge/skills/gaelic-ghost/socket/swift-package-extension-workflow.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 | $0.00046 | $0.01461 |
| Opus 5 | $0.00023 | $0.00731 |
| Sonnet 5 | $0.00009 | $0.00292 |
| Haiku 4.5 | $0.00005 | $0.00146 |
Grade A, and why
swift-package-extension-workflow 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 2d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swift Package Extension Workflow
Purpose
Own SwiftPM extension work that does not belong in ordinary package build/run or testing workflows. Keep package plugins, macros, traits, generated-source policy, permission review, and toolchain comparison in one package-first path, then hand off when Xcode-managed project context becomes authoritative.
When To Use
- Use this skill for build tool plugins, command plugins, plugin products, target plugin usage, and plugin commands.
- Use this skill for macro targets, macro declaration/implementation boundaries, expansion inspection, diagnostics, and macro tests.
- Use this skill for package traits, default traits, optional dependencies, conditional compilation, and trait-aware build/test matrices.
- Use this skill for generated sources, generated build products, plugin sandboxing, write access, or network permissions.
- Use this skill when the Swiftly-selected toolchain and Xcode-selected toolchain may differ.
- Recommend
swift-package-build-run-workflowfor ordinary manifests, dependencies, resources, builds, and executable runs. - Recommend
swift-package-testing-workflowwhen ordinary test organization or failure diagnosis is primary. - Recommend
format-swift-sourcesfor formatter-specific plugin operation after this skill establishes plugin permissions and ownership. - Recommend
xcode-build-run-workfloworxcode-testing-workflowwhen schemes, destinations, app hosts, Xcode project context, or Xcode-only evidence controls the result. - Recommend
explore-apple-swift-docswhen the task is documentation lookup rather than package mutation or execution.
Single-Path Workflow
- Inspect
Package.swift,Plugins/, macro targets, generated outputs, test targets, and any Xcode project or workspace markers. - Establish both toolchain identities before planning commands:
- Swiftly path:
swiftly use --print-location,swift --version, and relevantswift package,swift build, orswift testhelp. - Xcode path:
xcode-select -p,xcrun --find swift,xcrun swift --version, and matchingxcrun swift package, build, or test help. - If Swiftly is set to
xcode, record that bridge explicitly instead of presenting the two command paths as independent compiler distributions. - Do not assume the two toolchains expose identical SwiftPM commands, flags, manifest APIs, macro support, or plugin behavior.
- Swiftly path:
- Read the relevant official SwiftPM, Swift Evolution, or Apple/Xcode documentation and state the behavior relied on before editing.
- Classify the primary extension concern as
build-tool-plugin,command-plugin,macro,traits, orgenerated-source. - Run the managed FSX planner through the owning repository recipe for nearest-package resolution and a non-mutating command plan.
- Load only the reference needed for the selected concern:
- plugins:
references/package-plugins-build-command-and-xcode.md - permissions:
references/plugin-permissions-sandbox-and-outputs.md - macros:
references/swift-macros-package-shape.md - traits:
references/package-traits-feature-flags.md - generated files:
references/generated-source-and-build-products.md
- plugins:
- Use
references/cli-command-matrix.mdto keep Swiftly and Xcode commands distinct. - Use Xcode only when the requested operation changes an Xcode scheme, target, build phase, preview, or other Xcode-owned state; co-located Xcode files never change package routing.
- Validate the smallest relevant matrix first, then the supported Swift minor window and both host toolchains when the package claims both.
- Report the manifest/API floor, selected toolchain, commands run, generated or permission-sensitive outputs, and any handoff.
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.
- agents/openai.yaml 228 B
- references/cli-command-matrix.md 1.8 KB
- references/generated-source-and-build-products.md 1.2 KB
- references/package-plugins-build-command-and-xcode.md 2.1 KB
- references/package-traits-feature-flags.md 1.3 KB
- references/plugin-permissions-sandbox-and-outputs.md 1.5 KB
- references/snippets/apple-swift-package-core.md 15 KB
- references/swift-macros-package-shape.md 1.3 KB
- scripts/run-workflow.fsx 4.4 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.
- 2d ago First seen · 105 lines · 46 tokens per session scan A 812b0a985d71
swift-package-extension-workflow is a skill published in the GitHub repository gaelic-ghost/socket (7 stars, last pushed 9d ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,461 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
pipeline
Use when the user wants a feature idea taken end-to-end in one autonomous run — phrases like "run the whole pipeline", "take this feature from idea to finished branch", "brainstorm then build it autonomously", "do everything from idea to merged", "implement all phases without stopping". Triggers when they want…
craft
Use when a product idea is still vague and needs to become a clear definition of what to build — "let's craft an app like X", "help me define what I actually want", "clarify this idea before we plan it". Also use before planning or implementation when requirements, UX, domain behaviour, or technical preferences have…
bug-fix
Use when a bug, regression, or unexpected behaviour is reported and the user wants it fixed end to end — "why is X broken", "this stopped working after Y", "fix this crash". Also use when a symptom is known but its cause is not. Not for building new behaviour, and not for a change whose cause is already proven.
bug-investigate
Use when someone wants to know WHY something is broken and has not asked for it to be fixed — "why is this happening", "what's causing this error", "find out what's wrong", "diagnose this before we decide". Also use before committing to a fix, when the cause is unknown and the decision depends on it. Not for fixing …
setup
Use when superb's skills need their dependencies installed or checked — "set up superb", "install the dependencies", "why does pipeline say superpowers is missing", after a fresh plugin install, or on a new machine. Also use when a skill fails complaining that a superpowers sub-skill cannot be found.
phx-deps-audit
Audit Hex deps for supply-chain security risk — bidi chars, compile-time exec, maintainer changes, typosquats, CVEs. Use after mix deps.update, when checking if a package upgrade is safe, or reviewing mix.lock PR diffs.