agentic-engineering

A set of working rules for using Apple development tools safely in a coding repository. It directs different tasks to the appropriate command and requires approval before actions that change projects, publish apps, or affect accounts.

In plain words
What is it for?
Use it when searching Apple documentation, building or checking Apple projects, working with App Store Connect, or deciding whether a development action needs approval.
Why use it?
It reduces the risk of using the wrong tool or making an unintended change, such as uploading an app, altering signing settings, or committing code without approval.

Cursor rule for Cursor

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.

agentmods
npx agentmods add rules/abdullah4ai/apple-developer-toolkit/agentic-engineering
Clone the repo
git clone --depth 1 https://github.com/Abdullah4AI/apple-developer-toolkit

Made for: Cursor.

Per session 374 This file is loaded in full into every session.
When invoked 374 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00374 $0.00374
Opus 5 $0.00187 $0.00187
Sonnet 5 $0.00075 $0.00075
Haiku 4.5 $0.00037 $0.00037

Measured yesterday against content hash f154086df005, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentic-engineering 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 yesterday.

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.

.cursor/rules/agentic-engineering.mdc · 45 lines

What it actually says

Apple Developer Toolkit Agentic Engineering Rules

Apply these rules whenever Cursor works in this repository.

Route Tools Explicitly

  • Apple docs and WWDC lookup: use node cli.js from the repo.
  • App Store Connect work: use appledev store.
  • App scaffolding and fix loops: use appledev build.
  • Design/platform rules: read only the relevant references/, skills/ios-rules/, or skills/swiftui-guides/ files.

Side Effects Need Approval

Read-only commands are safe by default: docs search, symbols, doc, overview, samples, WWDC lookup, status, validate, diff, docs, doctor, and reference reads.

Ask before any mutation: App Store Connect writes, uploads, TestFlight/App Store publish, pricing, IAP, subscriptions, signing, devices, webhooks, notarization, Xcode Cloud runs, local project writes, simulator launches, hook installation, commits, pushes, PRs, merges, releases, or tags.

Never post to X/Twitter from this repository or skill.

Memory and Observability

  • Do not persist raw task logs, App Store state, generated code, build errors, credentials, or temporary decisions to long-term memory.
  • Keep run artifacts in repo-local files when needed.
  • Summarize what was checked, what changed, what did not change, and remaining risks.

Upstream Sync

After upstream sync commits, run:

bash scripts/apply-agentic-engineering.sh

Then check:

git diff --check -- README.md SKILL.md skills/apple-developer-toolkit/README.md
npx skills add . --list --full-depth
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. yesterday First seen · 45 lines · 374 tokens per session scan A f154086df005

Subscribe to this mod's changes

agentic-engineering is a cursor rule published in the GitHub repository Abdullah4AI/apple-developer-toolkit (10 stars, last pushed 4d ago), licensed MIT. It adds 374 tokens to every session, about $0.0019 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.