Xcode-Build-Optimization-Agent-Skill copilot-instructions.md

A set of instructions for an AI coding assistant reviewing and improving Xcode build performance. Xcode is Apple’s tool for building apps such as those for iPhone and Mac.

In plain words
What is it for?
It helps benchmark clean and incremental builds, find slow compilation areas, review build settings and scripts, and examine Swift Package Manager overhead.
Why use it?
It keeps build-performance work focused and evidence-based, while requiring developer approval before project or source changes are made.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/avdlee/xcode-build-optimization-agent-skill/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/AvdLee/Xcode-Build-Optimization-Agent-Skill

Made for: GitHub Copilot.

Per session 525 This file is loaded in full into every session.
When invoked 525 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00525 $0.00525
Opus 5 $0.00262 $0.00262
Sonnet 5 $0.00105 $0.00105
Haiku 4.5 $0.00052 $0.00052

Measured 2d ago against content hash a77d5d6d6c98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Xcode-Build-Optimization-Agent-Skill copilot-instructions.md 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.

.github/copilot-instructions.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot Instructions: Xcode Build Optimization Skills

Review changes as an Agent Skills expert and Xcode build optimization reviewer.

Repository Mission

Keep this repository focused on:

  • Xcode clean and incremental build benchmarking
  • compile hotspot analysis
  • build settings and scheme auditing
  • build script and dependency-analysis guidance
  • Swift Package Manager build overhead and module variant analysis

Do not turn the repository into general iOS architecture guidance or product documentation.

Agent Skill Requirements

  • Every skill directory must contain a SKILL.md with valid name and description frontmatter.
  • Descriptions must state both what the skill does and when to use it.
  • Keep SKILL.md concise and delegate deeper material to one-level-deep reference files.
  • Reference files should be discoverable from the matching SKILL.md.

Behavior Constraints

  • Default to recommend-first behavior.
  • Never introduce instructions that apply project, build-setting, or source changes without explicit developer approval.
  • Preserve evidence-driven workflows: command used, build type, target or package affected, and measured impact.
  • Prefer deterministic shell commands and structured artifacts over ad hoc prose.

Build Optimization Focus Areas

When reviewing changes, prioritize:

  1. Benchmark correctness

    • clean vs incremental builds are treated separately
    • warm-up and repetition rules are explicit
    • output artifacts are stored in .build-benchmark/
  2. Evidence quality

    • recommendations cite timing summaries, script phases, compiler diagnostics, or dependency data
    • estimated impact and confidence are separated from observed evidence
  3. Apple-aligned guidance

    • target dependencies and build order accuracy
    • script input/output declarations and .xcfilelist usage
    • DEFINES_MODULE, module maps, and framework-qualified imports
    • explicit module dependency and module variant reduction guidance
    • explicit type information and simpler expressions for Swift compile efficiency

Read the full file on GitHub · 70 lines

Changes

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.

  1. 2d ago First seen · 70 lines · 525 tokens per session scan A a77d5d6d6c98

Subscribe to this mod's changes

Xcode-Build-Optimization-Agent-Skill copilot-instructions.md is an instructions file published in the GitHub repository AvdLee/Xcode-Build-Optimization-Agent-Skill (1,212 stars, last pushed 20d ago), licensed MIT. It adds 525 tokens to every session, about $0.0026 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 2026-08-30.