Marcos Paulo
89 lines
6.6 KiB
Markdown
89 lines
6.6 KiB
Markdown
# Additional reading: multi-agent coding
|
||
|
||
Verified on 2026-09-02. Start with the official references for behavior and constraints; use the practitioner articles for concrete workflow ideas that should be tested against your own repository.
|
||
|
||
## Git worktrees and isolated coding sessions
|
||
|
||
### 1. [Git — `git-worktree` Documentation](https://git-scm.com/docs/git-worktree.html)
|
||
|
||
- **Publisher:** Git
|
||
- **Topic:** Worktree fundamentals and lifecycle
|
||
- **Teaching takeaway:** The authoritative reference for how linked worktrees share repository data while retaining separate `HEAD` and index state. Use its `add`, `list`, `lock`, `remove`, `prune`, and `repair` sections to teach the complete lifecycle rather than only worktree creation.
|
||
|
||
### 2. [Run parallel sessions with worktrees](https://code.claude.com/docs/en/worktrees)
|
||
|
||
- **Publisher:** Anthropic — Claude Code Docs
|
||
- **Topic:** Native worktree isolation for coding agents
|
||
- **Teaching takeaway:** Shows how Claude Code creates isolated sessions with `--worktree`, how gitignored environment files can be copied with `.worktreeinclude`, and how subagents can use worktree isolation. It is a useful bridge between raw Git commands and a real agent workflow.
|
||
|
||
### 3. [How Git Worktrees Transformed My AI Agent Development Workflow in 2026](https://medium.com/@mudassir00seven/how-git-worktrees-transformed-my-ai-agent-development-workflow-in-2026-ad8a59b8edfb)
|
||
|
||
- **Publisher:** Medium — Mudassir Khan
|
||
- **Topic:** One worktree per agent and task
|
||
- **Teaching takeaway:** A concise practitioner explanation of why parallel agents collide in a shared filesystem and how one task, branch, worktree, and pull request per agent reduces that interference. Pair it with the official Git documentation because operational details may evolve.
|
||
|
||
### 4. [How to Use Git Worktrees with Coding Agents](https://meshintelligence.substack.com/p/how-to-use-git-worktrees-with-coding)
|
||
|
||
- **Publisher:** Mesh Intelligence on Substack — Petar Djukic
|
||
- **Topic:** Worktree-per-task workflow and integration boundaries
|
||
- **Teaching takeaway:** Explains why branches alone do not isolate active files, compares worktrees with clones and containers, and presents a create-work-review-remove lifecycle. Its strongest lesson is that worktrees isolate execution, not merge conflicts, so scheduling and review gates still matter.
|
||
|
||
## Subagents and orchestration
|
||
|
||
### 5. [Create custom subagents](https://code.claude.com/docs/en/sub-agents)
|
||
|
||
- **Publisher:** Anthropic — Claude Code Docs
|
||
- **Topic:** Specialized subagents, context, tools, and background execution
|
||
- **Teaching takeaway:** Demonstrates how to define narrow subagents with their own prompts, tool permissions, and models, then run them in foreground or background. It supports teaching that delegation quality depends on explicit responsibility and context boundaries, not merely spawning more agents.
|
||
|
||
### 6. [Building Effective AI Agents](https://www.anthropic.com/engineering/building-effective-agents)
|
||
|
||
- **Publisher:** Anthropic Engineering
|
||
- **Topic:** Agent architecture patterns
|
||
- **Teaching takeaway:** Introduces routing, parallelization, orchestrator-worker, and evaluator-optimizer patterns while recommending the simplest architecture that meets the task. The orchestrator-worker section is especially useful for explaining when a strong planner should dynamically decompose work for bounded workers.
|
||
|
||
### 7. [How we built our multi-agent research system](https://www.anthropic.com/engineering/multi-agent-research-system)
|
||
|
||
- **Publisher:** Anthropic Engineering
|
||
- **Topic:** Production multi-agent coordination
|
||
- **Teaching takeaway:** A production case study in which a lead agent plans and delegates independent searches to parallel subagents. It is useful for discussing breadth-first tasks, separate context windows, token cost, evaluation, and why parallelism helps most when subtasks are genuinely independent.
|
||
|
||
### 8. [A practical guide to building agents](https://openai.com/business/guides-and-resources/a-practical-guide-to-building-ai-agents/)
|
||
|
||
- **Publisher:** OpenAI
|
||
- **Topic:** Manager and handoff orchestration patterns
|
||
- **Teaching takeaway:** Distinguishes centralized manager orchestration from decentralized handoffs and shows agents being exposed as tools to other agents. Use it to teach that the right topology depends on who must retain control, combine outputs, and own the final response.
|
||
|
||
### 9. [Agent orchestration](https://openai.github.io/openai-agents-python/multi_agent/)
|
||
|
||
- **Publisher:** OpenAI Agents SDK
|
||
- **Topic:** Agents-as-tools, handoffs, and code-driven workflows
|
||
- **Teaching takeaway:** Gives a precise comparison between a manager calling specialists as tools and handing control to a specialist. It also covers deterministic orchestration in code, including chains, evaluator loops, and parallel execution for independent tasks.
|
||
|
||
## Model routing and reusable skills
|
||
|
||
### 10. [Optimizing for cost and intelligence](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence)
|
||
|
||
- **Publisher:** Anthropic — Claude Platform Docs
|
||
- **Topic:** Routing work between frontier and lower-cost models
|
||
- **Teaching takeaway:** Compares model selection, advisor, and orchestrator strategies using cost-per-completed-task rather than token price alone. Its orchestrator guidance directly supports a frontier planner dispatching bulk independent work to cheaper workers—but also explains when one model is simpler and less expensive.
|
||
|
||
### 11. [Models](https://openai.github.io/openai-agents-python/models/)
|
||
|
||
- **Publisher:** OpenAI Agents SDK
|
||
- **Topic:** Per-agent model selection and mixed-provider routing
|
||
- **Teaching takeaway:** Documents how different agents in one workflow can use different models or providers and how routing can be configured centrally. This is a practical implementation reference for turning a conceptual “strong planner, lightweight workers” policy into explicit per-agent configuration.
|
||
|
||
### 12. [Skills](https://platform.claude.com/docs/en/managed-agents/skills)
|
||
|
||
- **Publisher:** Anthropic — Claude Platform Docs
|
||
- **Topic:** Reusable filesystem-based agent skills
|
||
- **Teaching takeaway:** Explains the `SKILL.md` package model, repository discovery, supporting scripts and resources, and why only task-relevant skills should be attached. It also highlights the security lesson that repository skills are executable instructions and therefore part of the agent’s trust boundary.
|
||
|
||
## Suggested teaching order
|
||
|
||
1. Learn the Git primitive with resources 1–2.
|
||
2. Compare real worktree-per-agent practices with resources 3–4.
|
||
3. Design bounded workers and orchestration with resources 5–9.
|
||
4. Add deliberate model routing and reusable skills with resources 10–12.
|