[pull] main from PaulDuvall:main#6
Merged
pull[bot] merged 8 commits intoTheTechOddBug:mainfrom Dec 11, 2025
Merged
Conversation
Analysis document was used for planning the restructure but is no longer needed now that the work is complete. The insights are captured in the git history and the restructured files themselves. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Removed references to ANALYSIS.md from directory structure and resources section since the file has been deleted. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Added blockquote at the top of examples README that links back to the main Issue Generation pattern definition in the root README.md. This helps users understand the pattern context and maturity level. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
…lopment Updated the main Issue Generation pattern definition to align with the examples directory that now uses <1 hour tasks for AI-assisted development. Changes: - Description: 4-8 hours → <1 hour for AI-assisted development - Mermaid diagram: <8 hours? → <1 hour? - Core Principles: <8 hours → <1 hour (AI-assisted development velocity) - Cycle Time Target: 4-8 hours → <1 hour with AI assistance - Anti-pattern examples: Updated time estimates to reflect AI velocity - OAuth endpoint: 8 hours → <1 hour with AI - WebSocket connection: 6 hours → 45 minutes - Unit tests: 4 hours → 30 minutes - Added AI-assisted note to good example Rationale: AI-assisted development fundamentally changes task velocity: - Traditional: Planning (30min) + Coding (6hrs) + Testing (1hr) = 8 hours - AI-Assisted: Planning (5min) + AI prompting (10min) + Review (20min) + Testing (15min) = 60 min See examples/issue-generation/ for detailed AI-first implementation guidance. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Added new section highlighting NOTES.md as the location for early-stage pattern exploration before formalization. This provides better visibility into emerging pattern ideas and the pattern development lifecycle. Changes: - Added Pattern Exploration section with link to NOTES.md - Explained purpose of NOTES.md for tracking exploratory patterns - Mentioned current explorations (voice-to-code, etc.) 📋 Change summary: * experiments/README.md: Added Pattern Exploration section (4 lines) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Changed from Kanban-focused to methodology-agnostic approach per Option 2. Main README.md changes: - Description: "Kanban-optimized" → "small, deployable work items" - Added Methodology Note: Pattern works with Kanban, Scrum, or ad-hoc workflows - Core Principles: "Kanban Optimization" → "Small Batch Sizing" - Mermaid diagram: "Kanban Card Creation" → "Work Item Creation" - Moved Kanban references to optional context section - Reordered quotes: Agile Alliance first, Kanban context separate examples/issue-generation/README.md changes: - Title: "Kanban-optimized issues" → "small, deployable work items" - Pattern Definition: Added "Works with any methodology" note - Added "Methodology-Agnostic" callout to Why <1 Hour Tasks - Core Principles: Added "Works with any methodology" note Rationale: - Core pattern is AI-assisted task decomposition, not Kanban - Works equally well with Scrum, continuous delivery, etc. - Prevents confusion that users need full Kanban implementation - Keeps Kanban context as helpful reference, not requirement 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Add new experimental pattern for managing AI assistant configuration files by loading rules incrementally based on task context. This pattern addresses instruction saturation and context bloat in files like CLAUDE.md. Key features: - Three-tier architecture (main file + specialized rules + routing) - Decision framework with mermaid diagram - Integration with Event Automation and Custom Commands - Three anti-patterns: Bloated Configuration, Over-Fragmentation, No Loading Guidance - Validation metrics and success criteria Pattern placed in Advanced Workflows section between Custom Commands and Asynchronous Research as Intermediate maturity level. Based on HumanLayer research on context engineering and instruction limits. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Update Progressive Disclosure pattern to make it clear the pattern applies to any AI coding assistant configuration file, not just Claude/CLAUDE.md. Changes: - Description now mentions "across any AI coding assistant (Claude Code, Cursor, Aider, etc.)" - Core Problem section uses "AI coding assistants" instead of "Claude Code" specifically - Examples mention CLAUDE.md, AGENTS.md, .cursorrules, .aiderules, etc. - Directory structure clarifies CLAUDE.md is one example among many - Main Rules File section renamed from "Main Rules File (CLAUDE.md)" to generic "Main Rules File" - Hook configuration labeled as "example for Claude Code, adapt for your AI assistant" - Anti-patterns updated to show applicability across all configuration file types CLAUDE.md remains the primary example throughout, but context makes clear this is a universal pattern applicable to OpenCode, Zed, Cursor, Aider, and other AI coding assistants. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
See Commits and Changes for more details.
Created by
pull[bot] (v2.0.0-alpha.4)
Can you help keep this open source service alive? 💖 Please sponsor : )