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/markdavidgan/apple-dev-skills/gemini-mdgit clone --depth 1 https://github.com/markdavidgan/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/instructions/markdavidgan/apple-dev-skills/gemini-md)<a href="https://agentmods.dev/instructions/markdavidgan/apple-dev-skills/gemini-md"><img src="https://agentmods.dev/badge/instructions/markdavidgan/apple-dev-skills/gemini-md.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 | $0.02458 | $0.02458 |
| Opus 5 | $0.01229 | $0.01229 |
| Sonnet 5 | $0.00492 | $0.00492 |
| Haiku 4.5 | $0.00246 | $0.00246 |
Grade A, and why
apple-dev-skills GEMINI.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 5d 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.
This is a copy
94% identical to apple-dev-skills AGENTS.md — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Dev Skills — Agent Guide (Gemini / Antigravity / Agy)
Cross-CLI copy of the project guide, generated verbatim from
CLAUDE.md. Read by Gemini CLI, Antigravity, and Agy.Tool mapping: Claude Code's
Skill/Agent/Read/Edit/Bashtools map to your CLI's equivalents (Gemini activates skills viaactivate_skill). Skills are markdown files discovered from.agents/skills/or~/.gemini/.... Subdirectories are flattened with__separators — see "Cross-Platform Constraints" below.
This is the standalone Apple development skill repository. It is not part of aether-agent-plugins.
Quick Reference
| Task | Command |
|---|---|
| Validate source | node scripts/validate.js |
| Build platforms | node scripts/build.js |
| Install locally | ./install.sh --platform claude --local |
| Install globally | ./install.sh --platform claude |
Repository Rules
- Edit source, not generated platform bundles — skill/agent/command changes begin in
src/. Never hand-editplatforms/,.claude-plugin/, or.cursor-plugin/; they are generated byscripts/build.js. - Run validation before committing —
node scripts/validate.jsmust pass. - Regenerate after source edits — After changing any
src/file, runnode scripts/build.jsand commit source + generated outputs together. - Keep skills self-contained — Cross-reference other skills by name, not by installation-specific file path.
- YAML frontmatter is required — Every
SKILL.md, agent, and command must have valid frontmatter. - Stay machine-agnostic — Never commit absolute clone paths or credentials.
src/mcp/*/mcp.jsonmust keep placeholders/env-var references; real paths/keys belong in machine-local client config. - Product repositories own their overlays. Generic methodology belongs here; consumer repos commit only their product/repository-specific binding layer.
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.
- 5d ago First seen · 247 lines · 2,458 tokens per session scan A 9ef06c1de022
apple-dev-skills GEMINI.md is an instructions file published in the GitHub repository markdavidgan/apple-dev-skills (5 stars, last pushed 6d ago), licensed MIT. It adds 2,458 tokens to every session, about $0.0123 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to apple-dev-skills AGENTS.md, differing in 11 lines, and is treated as a copy.
Other instructions, from other repositories
app-store-connect-mcp AGENTS.md
AGENTS.md instructions for erayendes/app-store-connect-mcp, covering agents.md, what this is, if a user asks you to install it, 1. agree on the profiles, then register them and 2. send the user to setup for the credentials.
roblox-brain AGENTS.md
AGENTS.md instructions for TabooHarmony/roblox-brain, covering agents.md: guide for ai agents and contributors, what this repo is, architecture: progressive disclosure, skill file structure and skill title.
agentdex CLAUDE.md
Instructions for CaptainYouz/agentdex, covering claude.md — agentdex, purpose, commands, architecture and what gets scanned.
alphaloop AGENTS.md
Instructions for realnaka/alphaloop, covering alphaloop — agent instructions, what you are looking at, quick install (any agent), how to use as an agent and key files in this repo.
template GEMINI.md
Instructions for ai-plugin-marketplace/template, covering skill evaluator, usage and how it works.
skene-cookbook AGENTS.md
Instructions for SkeneTechnologies/skene-cookbook, covering agents.md, quick context, build & test commands, install dependencies and run tests (full suite).