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 instructions/avdlee/xcode-build-optimization-agent-skill/agents-mdgit clone --depth 1 https://github.com/AvdLee/Xcode-Build-Optimization-Agent-SkillWhat 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 | $0.00740 | $0.00740 |
| Opus 5 | $0.00370 | $0.00370 |
| Sonnet 5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
Xcode-Build-Optimization-Agent-Skill AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidance
This is a multi-skill Xcode build optimization repository.
Layout
skills/contains six installable Agent Skills, each with aSKILL.mdentrypoint. Each skill bundles its own scripts, references, and schemas so it works after standalone installation.references/,schemas/, andscripts/at the repo root are canonical copies of the shared support files. Changes to these must be synced into the skill folders that use them (see CONTRIBUTING.md)..claude-plugin/contains plugin and marketplace metadata.
Skills
| Skill | Purpose |
|---|---|
xcode-build-benchmark |
Repeatable clean and incremental build benchmarking |
xcode-compilation-analyzer |
Swift compile hotspot analysis and source-level recommendations |
xcode-project-analyzer |
Build settings, scheme, script phase, and target dependency auditing |
spm-build-analysis |
Package graph, plugin overhead, and module variant review |
xcode-build-orchestrator |
Orchestrator: benchmark, analyze, prioritize, approve, delegate fixes, re-benchmark |
xcode-build-fixer |
Apply approved optimization changes and verify with benchmarks |
Rules
- Wall-clock build time (how long the developer waits) is the primary success metric. Every recommendation must state its expected impact on wall-clock time. If the impact cannot be predicted, say so.
- Cumulative task time from the Build Timing Summary is diagnostic evidence, not proof of wall-time impact. Xcode parallelizes aggressively, so reducing parallel task time may produce zero wait-time improvement.
- Recommend-first by default. Never apply project, source, or package changes without explicit developer approval.
- Benchmark before optimizing. Use
.build-benchmark/artifacts as evidence. - Treat clean and incremental builds as separate metrics.
- The orchestrator (
xcode-build-orchestrator) is the primary entrypoint for end-to-end work. - Each skill bundles its own copies of scripts, references, and schemas for standalone installation. Root-level
scripts/,references/, andschemas/are the canonical copies; keep both layers in sync.
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 · 42 lines · 740 tokens per session scan A 93c765ee33fb
Xcode-Build-Optimization-Agent-Skill AGENTS.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 740 tokens to every session, about $0.0037 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.
Other instructions, from other repositories
iOS-Design-Agent-Skill AGENTS.md
Instructions for vermont42/iOS-Design-Agent-Skill, covering agent guidelines, in scope and out of scope.
AppClaw CLAUDE.md
Instructions for appclawhq/AppClaw, covering claude.md, what is appclaw?, build & run commands, architecture and entry point & cli modes (src/index.ts).
webflow-skills CLAUDE.md
Instructions for webflow/webflow-skills, covering project overview, repository structure, ci validation, what ci checks and 2. marketplace and plugin configs exist.
rolecraft AGENTS.md
Instructions for rolecraft-sh/rolecraft, covering rolecraft — development guidelines, ⚠️ startup checklist (read before every task), workflow, interaction rules and code style.
MathModelAgent CLAUDE.md
Claude Code instructions for jihe520/MathModelAgent, covering claude.md, 项目概述, commands, 后端 and 安装依赖.
lime AGENTS.md
AGENTS.md instructions for limecloud/lime, covering lime 源码仓库指南, 事实源, 工程约束, 协议与质量 and 执行方式.