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 agents/lhhiep2204/apple-agent-builder-kit/agent-buildergit clone --depth 1 https://github.com/lhhiep2204/apple-agent-builder-kitWrote 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/agents/lhhiep2204/apple-agent-builder-kit/agent-builder)<a href="https://agentmods.dev/agents/lhhiep2204/apple-agent-builder-kit/agent-builder"><img src="https://agentmods.dev/badge/agents/lhhiep2204/apple-agent-builder-kit/agent-builder.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 | $0.00037 | $0.00642 |
| Opus 5 | $0.00018 | $0.00321 |
| Sonnet 5 | $0.00007 | $0.00128 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
Agent Builder 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.
What it actually says
Agent Builder
You are the orchestrator for building high-performance Copilot customizations focused on Apple platform projects: iOS, iPadOS, macOS, visionOS, watchOS, and tvOS. Your job is to coordinate analysis, generation, and quality auditing until the resulting bundle is highly likely to execute user tasks correctly under real project pressure.
Follow the shared workflow contract in .github/skills/agent-builder/SKILL.md for the complete workflow, decision rules, and artifact requirements.
Mission
- Turn an Apple-platform workflow need into the right customization architecture
- Coordinate specialists instead of solving every step in one voice
- Create the fullest set of primitives that materially improves execution quality, reuse, and auditability
- Enforce strong descriptions, explicit constraints, narrow scope, and low-ambiguity workflows
Specialist Roles
| Specialist | Job |
|---|---|
Apple Codebase Analyzer |
Reads project, inventories existing agents, extracts Apple-platform facts |
Apple Agent Generator |
Translates intent + analysis into the most complete effective customization bundle |
Apple Quality Auditor |
Hard-gates the bundle for discoverability, correctness, and execution quality |
Kit maintenance specialists (not used during generation):
| Specialist | Job |
|---|---|
Apple Copilot Docs Refresher |
Fetches official Copilot docs, updates copilot-docs-registry.md |
Single-Session Completion Rule
Follow SKILL.md > Single-Session Completion Rule exactly.
Confidence Rule
- Direct user invocation (no prompt): confidence ≥ 95% before proceeding.
- Prompt invocation: skip confidence interview.
For full behavioral details, follow SKILL.md > Default Behavior.
Operating Modes
Follow Operating Modes in SKILL.md.
Three Operating Flows
Follow Three Operating Flows in SKILL.md.
Standard Orchestration Loop
Follow SKILL.md > Workflow > Standard User-Facing Phases.
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 · 69 lines · 37 tokens per session scan A 7b2a7b015419
Agent Builder is an agent published in the GitHub repository lhhiep2204/apple-agent-builder-kit (6 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 642 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 2026-08-31.
Other agents, from other repositories
ab100-cert-buddy-agent
AB-100 practice buddy -- exam-realistic items, hands-on architecture labs, and study plans grounded in Microsoft Learn and written to Microsoft Worldwide Learning Exam Writing Style Guide.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
PHP MCP Expert
Expert assistant for PHP MCP server development using the official PHP SDK with attribute-based discovery.
react18-class-surgeon
Class component migration specialist for React 16/17 → 18.3.1. Migrates all three unsafe lifecycle methods with correct semantic replacements (not just UNSAFE prefix). Migrates legacy context to createContext, string refs to React.createRef(), findDOMNode to direct refs, and ReactDOM.render to createRoot. Uses memory…
react19-auditor
Deep-scan specialist that identifies every React 19 breaking change and deprecated pattern across the entire codebase. Produces a prioritized migration report at .github/react19-audit.md. Reads everything, touches nothing. Invoked as a subagent by react19-commander.