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/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/instructions/lhhiep2204/apple-agent-builder-kit/agent-builder)<a href="https://agentmods.dev/instructions/lhhiep2204/apple-agent-builder-kit/agent-builder"><img src="https://agentmods.dev/badge/instructions/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 | $0.01150 | $0.01150 |
| Opus 5 | $0.00575 | $0.00575 |
| Sonnet 5 | $0.00230 | $0.00230 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade A, and why
apple-agent-builder-kit agent-builder.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 4d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customization File Standards
Apply these rules when editing Copilot customization files in this repository.
File Purpose
- Each file should serve one primary purpose
- Prefer composition across agent, skill, instruction, and prompt files instead of one overloaded file
- Do not create extra artifacts unless they improve execution quality or reuse
Frontmatter
Follow all YAML frontmatter rules in SKILL.md > YAML Frontmatter Generation. Verify keys against the allowlist in copilot-docs-registry.md.
Additional rules specific to instruction file editing:
- Use
applyToonly for guidance that should load automatically; keep narrow - Consider
excludeAgentto limit instruction to coding-agent or code-review usage - Quote
descriptionvalues when punctuation could break parsing
Writing Standard
- Prefer explicit operating rules over broad aspirations
- State goals and non-goals when ambiguity is likely
- Define decision criteria when multiple primitives are possible
- Include validation checklists for complex or failure-prone workflows
- Keep examples realistic and domain-specific
- If the customization targets Apple projects, make platform assumptions and framework defaults explicit
- Prefer Apple-specific terminology over generic mobile phrasing when the scope is Apple-only
Primitive Selection
Use the matching scaffold template in .github/templates/agent-builder/. Replace all <...> placeholders with project-specific content.
- Agent:
agent-template.md| Skill:skill-template.md| Instruction:instruction-template.md| Prompt:prompt-template.md| Hook:hook-checklist.md
For primitive selection decisions, apply primitive-decision-matrix.md. For role naming, reference apple-role-catalog.md.
Quality Checks
Before finalizing any non-trivial customization file, run the checklist in .github/templates/agent-builder/agent-audit-rubric.md. A file passes when it is specific, discoverable, and correctly scoped — not merely readable.
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.
- 4d ago First seen · 104 lines · 1,150 tokens per session scan A 4e9bcab2f607
apple-agent-builder-kit agent-builder.instructions.md is an instructions file published in the GitHub repository lhhiep2204/apple-agent-builder-kit (6 stars, last pushed 4mo ago), licensed MIT. It adds 1,150 tokens to every session, about $0.0057 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 instructions, from other repositories
ab100 CLAUDE.md
Instructions for timothywarner-org/ab100, covering claude.md, repository purpose, slide deck build, source decks (microsoft ab-100t00) and course structure (4 hours).
ab100 AGENTS.md
Instructions for timothywarner-org/ab100, covering agents.md, repository purpose, source of truth, course structure and poc app.
ab100 copilot-instructions.md
Instructions for timothywarner-org/ab100, covering copilot instructions, repository purpose, key locations, skill and agent conventions and mcp server ids.
spec-kitty AGENTS.md
AGENTS.md instructions for Priivacy-ai/spec-kitty, covering spec kitty development guidelines, ⚠️ critical: load the project charter first, ⚠️ critical: template source location, ⚠️ critical: use canonical sources, never improvise and ⚠️ critical: git workflow — no direct pushes to origin/main.
apm python.instructions.md
Python development guidelines.
apex-accelerator vendor-prompting.instructions.md
Vendor prompting best-practice rules for Anthropic Claude and OpenAI GPT-5.6-Terra agents and prompts. Each rule cites a rule ID in the vendor-prompting skill rules.json registry. Validator: npm run lint:vendor-prompting.