agent-builder

agent-builder is a skill for Claude Code, Codex from lhhiep2204/apple-agent-builder-kit. It costs 40 tokens per session (8,405 once invoked), scanned A, original, MIT.

A toolkit for creating, improving, checking, or troubleshooting custom Copilot agents, skills, instructions, prompts, and hooks for Apple software projects.

In plain words
What is it for?
Use it to build or audit Copilot customisation bundles, including Apple-focused agents and their supporting instructions.
Why use it?
It provides shared rules and workflows for producing consistent agent customisations that fit Apple development and agile delivery work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to build or audit Copilot customisation bundles, including Apple-focused agents and their supporting instructions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lhhiep2204/apple-agent-builder-kit/agent-builder
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.

Any agent
npx skills add lhhiep2204/apple-agent-builder-kit --skill agent-builder
Clone the repo
git clone --depth 1 https://github.com/lhhiep2204/apple-agent-builder-kit

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for agent-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/lhhiep2204/apple-agent-builder-kit/agent-builder.svg)](https://agentmods.dev/skills/lhhiep2204/apple-agent-builder-kit/agent-builder)
Your own site
<a href="https://agentmods.dev/skills/lhhiep2204/apple-agent-builder-kit/agent-builder"><img src="https://agentmods.dev/badge/skills/lhhiep2204/apple-agent-builder-kit/agent-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,405 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00040 $0.08405
Opus 5 $0.00020 $0.04202
Sonnet 5 $0.00008 $0.01681
Haiku 4.5 $0.00004 $0.00840

Measured 7d ago against content hash 7e14f13df42b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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 7d 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/skills/agent-builder/SKILL.md · 582 lines

How it starts

The opening of the file, as written. The whole thing — 582 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Builder

Consumers:

  • Agent Builder in .github/agents/agent-builder.agent.md (conductor)
  • Apple Agent Generator in .github/agents/apple-agent-generator.agent.md (artifact requirements, bundle shapes)
  • Apple Quality Auditor in .github/agents/apple-quality-auditor.agent.md (audit standard, minimums)
  • Apple Codebase Analyzer in .github/agents/apple-codebase-analyzer.agent.md (analysis template, workflow signals)
  • .github/instructions/agent-builder.instructions.md (generation quality standards, file editing rules)

Use this skill to design and generate high-quality Copilot customization bundles for Apple platform projects. This is the single source of truth for the complete kit workflow, bundle shapes, and artifact behavioral requirements.

Section Index

Section What it covers
Use Cases When to invoke this skill
Apple Scope Platforms, fallback defaults, alignment rule
Operating Modes / Three Operating Flows Discovery vs Fast, Greenfield vs Verify vs Extend
Default Behavior Generation defaults, tool restrictions, alignment
Single-Session Completion Rule Never abandon mid-workflow, vscode_askQuestions
Workflow 6-phase standard flow, kit reference files, community skill discovery
Bundle Shapes Single / Focused / Full Kit minimums
Artifact Requirements Per-primitive rules: Agent, Skill, Instruction, Prompt, Hook, YAML Frontmatter
Generation Principles 8 non-negotiable rules for every generated agent
Harness Engineering Alignment Feedforward/feedback, control types, key patterns
Large Task Execution Pattern Decomposition, chunked execution, persistence
Context Optimization Rules Three-layer model, signal-to-noise, context budget
Bundle Evolution Guidance Maintenance triggers table for generated project context instruction
Constitution Pattern Structure, generation rules, Phase -1 gates
Spec-Driven Pipeline 4-stage pipeline, templates, activation criteria
Separated Review Pipeline 4-agent review, short-circuit, evidence standard
Handoffs Pattern Frontmatter format, delegation rules
Evidence Standard Labels, enforcement, flow
Bundle Evolution and Drift Detection Ref to Bundle Evolution Guidance (same content)
Review Memory Promotion Recurring findings → durable rules
Hooks Generation Auto-format, lint, compile hooks
Generated File Marking Marker placement rules
Cross-Session Persistence Repo memory, session memory, progress format

Read the full file on GitHub · 582 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. 7d ago First seen · 582 lines · 40 tokens per session scan A 7e14f13df42b

Subscribe to this mod's changes

agent-builder is a skill published in the GitHub repository lhhiep2204/apple-agent-builder-kit (6 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 8,405 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.

Related

Other skills, from other repositories

write-epic

Produces a complete epic definition following Atlassian agile guidance. An epic captures a large initiative that is too big for a single sprint and must be decomposed into user stories.

MarieLynneBlock/arcanum-artifex · 40 tokens

write-user-story

Produces a complete, ready-to-groom user story following the standard Atlassian/agile format. It applies the INVEST criteria and the 3 Cs framework (Card, Conversation, Confirmation) to ensure each story is well-scoped, valuable, and testable — not just syntactically correct.

MarieLynneBlock/arcanum-artifex · 64 tokens

rework-rate

Measure and interpret PR rework rate — the emerging 5th DORA metric.

bradygaster/squad · 20 tokens

spec-kitty-charter-doctrine

Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…

Priivacy-ai/spec-kitty · 135 tokens

asc-subscription-localization

Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.

rorkai/app-store-connect-cli-skills · 60 tokens

foundation-models

On-device LLM integration using Apple's Foundation Models framework. Use when implementing AI text generation, structured output, or tool calling.

rshankras/claude-code-apple-skills · 29 tokens