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 Syniox5334/apple-dev-skills --skill apple-xcode-workflowgit clone --depth 1 https://github.com/Syniox5334/apple-dev-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/syniox5334/apple-dev-skills/apple-xcode-workflow)<a href="https://agentmods.dev/skills/syniox5334/apple-dev-skills/apple-xcode-workflow"><img src="https://agentmods.dev/badge/skills/syniox5334/apple-dev-skills/apple-xcode-workflow/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/syniox5334/apple-dev-skills/apple-xcode-workflow"><img src="https://agentmods.dev/badge/skills/syniox5334/apple-dev-skills/apple-xcode-workflow.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 | $0.00046 | $0.01317 |
| Opus 5.5 | $0.00018 | $0.00527 |
| Sonnet 5.5 | $0.00009 | $0.00263 |
| Haiku 4.5 | $0.00005 | $0.00132 |
Grade A, and why
apple-xcode-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 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Xcode Workflow
Purpose
Use this skill as the top-level entry point for Apple and Swift work in or around Xcode. The skill guides agent-side tool use, while scripts/run_workflow.py enforces local policy, mutation guards, cooldown behavior, docs routing, and structured fallback planning.
When To Use
- Use this skill for Xcode workspace inspection, read or search, diagnostics, build, test, and run tasks.
- Use this skill for Swift toolchain checks and official Apple CLI fallback.
- Use this skill for Apple and Swift documentation requests that should prefer Dash local sources before official web docs.
- Use this skill when direct filesystem mutation in an Xcode-managed scope may be required.
- Recommend
apple-dash-docsetswhen the user needs Dash docset search, install, or generation work instead of Apple execution work. - Recommend
apple-swift-package-bootstrapwhen the user needs to create a brand new Swift package rather than work inside an existing Xcode or Swift project.
Single-Path Workflow
- Classify the request into one operation type:
- workspace or session inspection
- read, search, or diagnostics
- build, test, or run
- package or toolchain management
- docs lookup
- mutation
- Run
scripts/run_workflow.pyto apply runtime configuration, mutation-guard checks, docs-routing order, advisory cooldown, and CLI fallback planning. - Use the guidance in
references/mcp-tool-matrix.mdfor agent-executed MCP operations. - If MCP fails, use the structured fallback output from
scripts/run_workflow.pytogether withreferences/cli-fallback-matrix.md. - Report which parts were agent-executed, which parts were locally enforced by script, and any required next step.
Inputs
operation_type: one of the operation types listed above.workspace_path: optional absolute path for the target Xcode or Swift workspace.tab_identifier: optional MCP tab identifier when already known.mcp_failure_reason: optional input when continuing from an earlier MCP failure.docs_query: required whenoperation_typeisdocs.filesystem_fallback_opt_in: optional explicit opt-in when planning direct filesystem fallback in Xcode-managed scope.- Defaults:
- runtime entrypoint:
python3 scripts/run_workflow.py - agent-side MCP retries once for transient failures
- advisory cooldown is
21days - docs source order is
dash-mcp,dash-local,official-web - mutation operations require the explicit guard in Xcode-managed scope
- runtime entrypoint:
What ships with it
20 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 322 B
- references/allowlist-guidance.md 514 B
- references/cli-fallback-matrix.md 909 B
- references/customization-flow.md 2.2 KB
- references/customization.template.yaml 258 B
- references/dash-docs-flow.md 573 B
- references/mcp-failure-handoff.md 1.2 KB
- references/mcp-setup-advisory.md 578 B
- references/mcp-tool-matrix.md 739 B
- references/mutation-risk-policy.md 861 B
- references/mutation-via-mcp.md 366 B
- references/skills-discovery.md 471 B
- references/skills-installation.md 492 B
- references/snippets/apple-swift-core.md 2.3 KB
- references/toolchain-management.md 702 B
- references/workflow-policy.md 1.1 KB
- scripts/advisory_cooldown.py 1.9 KB runs code
- scripts/customization_config.py 6.1 KB runs code
- scripts/detect_xcode_managed_scope.sh 982 B runs code
- scripts/run_workflow.py 11 KB runs code
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 · 124 lines · 46 tokens per session scan A 8a02cca4eea8
apple-xcode-workflow is a skill published in the GitHub repository Syniox5334/apple-dev-skills (5 stars, last pushed 25d ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,317 once invoked, about $0.0002 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 2026-08-31.
apple-xcode-workflow compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| apple-xcode-workflowSyniox5334/apple-dev-skills | Skill | 5 | 25d ago | Apache-2.0 | A | 46 | Codex |
| apple-engineer-superpowerspiemonte/apple-engineer-superpowers | Skill | 28 | 8mo ago | MIT | A | 82 | Claude Code |
| wear-compose-m3android/skills | Skill | 10k | 2d ago | Apache-2.0 | A | 91 | Claude Code |
| ink-custom-brush-builderandroid/skills | Skill | 10k | 2d ago | Apache-2.0 | A | 159 | Claude Code |
| kotlin-specialistJeffallan/claude-skills | Skill | 12k | 8d ago | MIT | A | 86 | Claude Code |
| swiftui-devOrkas-AI/Orkas | Skill | 9.1k | today | MIT | A | 3 | Claude Code, Codex |
| build-android-binarymicrosoft/power-platform-skills | Skill | 1.1k | today | MIT | A | 150 | Claude Code |