marketing-shibata50/claude-code-ultimate-guide
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docs: add context packing tools section and Osmani workflow reference

Browse source 
- New section "12. Context Packing Tools" in ai-ecosystem.md
  documenting gitingest, repo2txt usage patterns
- Added Addy Osmani "My AI Coding Workflow in 2026" to methodologies.md
  sources (validates spec-first, TDD, git checkpoints)
- Updated reference.yaml with ai_ecosystem_context_packing entry

Source: https://addyosmani.com/blog/ai-coding-workflow/

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Florian BRUNIAUX 2026-01-22 21:59:28 +01:00
parent ace62f2f84
commit 2a63230c95
4 changed files with 50 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

38
guide/ai-ecosystem.md
View file

@ -19,6 +19,8 @@
- [8. Workflow Orchestration](#8-workflow-orchestration)
- [9. Cost & Subscription Strategy](#9-cost--subscription-strategy)
- [10. Claude Cowork (Research Preview)](#10-claude-cowork-research-preview)
- [11. AI Coding Agents Matrix](#11-ai-coding-agents-matrix)
- [12. Context Packing Tools](#12-context-packing-tools)
- [Appendix: Ready-to-Use Prompts](#appendix-ready-to-use-prompts)
- [Alternative Providers (Community Workarounds)](#alternative-providers-community-workarounds)
@ -1111,6 +1113,42 @@ An **interactive comparison matrix** of 23 AI coding agents across 11 technical
---
## 12. Context Packing Tools
When working with LLMs on large codebases, **context packing** refers to techniques for extracting and feeding relevant code context to the model efficiently.
### Why Context Matters
Claude Code automatically reads files as needed, but external tools exist for:
- **Pre-session preparation**: Dump relevant code before starting
- **Cross-tool workflows**: Feed context to models outside Claude Code
- **Offline analysis**: Prepare context for later use
### Available Tools
| Tool | Purpose | How It Works |
|------|---------|--------------|
| **gitingest** | Repo → text dump | Extracts relevant files into a single text file for LLM consumption |
| **repo2txt** | Repo → formatted context | Similar to gitingest, with formatting options |
| **Context7 MCP** | Docs lookup | Fetches library documentation on-demand (see [MCP section](./ultimate-guide.md#mcp-servers)) |
### When to Use (and When Not)
| Scenario | Best Approach |
|----------|---------------|
| Working in Claude Code | Let Claude read files naturally — no pre-dumping needed |
| Feeding context to ChatGPT/Gemini | gitingest/repo2txt useful |
| Preparing spec for team review | Export relevant files to share |
| Very large monorepo (>1M LOC) | May help with selective extraction |
> **Note**: Claude Code's native file access is usually sufficient. These tools are most useful for cross-tool workflows or when working with models that don't have file system access.
### Source
- Addy Osmani: [My AI Coding Workflow in 2026](https://addyosmani.com/blog/ai-coding-workflow/) — Discusses context packing as part of a broader AI development workflow
---
## Alternative Providers (Community Workarounds)
> ⚠️ **Disclaimer**: This section documents techniques that exist in the community

1
guide/methodologies.md
View file

@ -310,6 +310,7 @@ Recommended stacks by situation:
**SDD & Spec-First**
- Addy Osmani: [How to Write Good Specs for AI Agents](https://addyosmani.com/blog/good-spec/)
- Addy Osmani: [My AI Coding Workflow in 2026](https://addyosmani.com/blog/ai-coding-workflow/) — End-to-end workflow: spec-first, context packing, TDD, git checkpoints
- Martin Fowler: [SDD Tools Analysis](https://martinfowler.com/articles/exploring-gen-ai/sdd-3-tools.html)
- InfoQ: [Spec-Driven Development](https://www.infoq.com/articles/spec-driven-development/)
- Kinde: [Beyond TDD - Why SDD is the Next Step](https://kinde.com/learn/ai-for-software-engineering/best-practice/beyond-tdd-why-spec-driven-development-is-the-next-step/)