# AI For Dummies — reference bundle

Research captured 2026-09-02. Official documentation is primary; practitioner
articles are context, not authority.

## Primary documentation

- Anthropic — custom subagents: https://code.claude.com/docs/en/sub-agents
  Separate context, tools, permissions, model selection, and worktree isolation.
- Anthropic — skills: https://code.claude.com/docs/en/skills
  Reusable instruction packages and skill discovery.
- Anthropic — worktrees: https://code.claude.com/docs/en/worktrees
  Isolated sessions, branches, cleanup, and ignored files.
- OpenAI — build skills: https://developers.openai.com/codex/skills
  Packaged instructions and resources for Codex workflows.
- OpenAI API — skills reference: https://developers.openai.com/api/reference/go/resources/skills
  Creating, versioning, listing, and downloading skill bundles.
- Git — worktree: https://git-scm.com/docs/git-worktree.html
  Linked working trees, branches, shared history, add/list/remove/prune.

## Research and articles

- [Model routing and reasoning controls](model-routing.md) — official OpenAI,
  Anthropic, and Google terminology, commands, compatibility caveats, and a
  practical tier/effort baseline.
- [Verified skill sources](skill-sources.md) — pinned GitHub references,
  package paths, local-match confidence, and an approval-first install prompt.

For a structured 12-part reading path—including Git and Anthropic documentation,
OpenAI orchestration guidance, Medium, and Substack—see
[additional-reading.md](additional-reading.md).

- Infobip Research — phased coding-agent workflow: https://arxiv.org/abs/2608.30701
- Effective asynchronous software engineering agents: https://arxiv.org/abs/2603.21489
- Launch Receipts — AI coding workflow without losing control: https://launchreceipts.com/articles/ai-coding-agent-workflow
- GitWorktree.org — three agents, three worktrees case study: https://www.gitworktree.org/cases/parallel-ai-agents

## Teaching claims

- Use a stronger model where ambiguity, architecture, decomposition, and review dominate.
- Use faster models for bounded implementation with explicit context and checks.
- Give every editing worker an isolated branch/worktree; merge only reviewed diffs.
- A skill is a reusable procedure plus optional references/scripts/assets, not magical memory.
- Delegation does not remove human responsibility for intent, boundaries, or evidence.