claudemd pattern

11 articles · 15 co-occurring · 0 contradictions · 0 briefs

Documentation explicitly describes CLAUDE.md auto-discovery in file directory and parent directories as context injection mechanism

Related concepts

tool integration patterns 9 context window management 8 state management 4 prompt engineering 4 prompt architecture 4 workflow automation 3 multi agent orchestration 3 context window optimization 3 session persistence 2 tool integration 1 tool context fit 1 task decomposition 1 system prompts 1 session state persistence 1 session management 1

Evidence chain (11 articles, showing 11)

Common workflows - Claude Code Docs example_of

Documentation explicitly describes CLAUDE.md auto-discovery in file directory and parent directories as context injection mechanism

@doodlestein: Useful prompt: example_of

AGENTS.md is a direct analogue to CLAUDE.md—both are structured files that serve as persistent context containers. The pattern is identical: encode key information/lessons into a file that travels wit

You're Using Claude Wrong! Here's How to be Ahead of 99% of Users example_of

Article explicitly uses CLAUDE.md as session persistence mechanism—storing 'project structure, preferences, and past decisions' to prevent interaction reset

Build with Claude Code | Paddle Developer Docs example_of

Provides concrete CLAUDE.md implementation with domain-specific conventions for Paddle API, showing how system prompt architecture encodes context

@alexalbert__: We've reset usage limits across our products! example_of

Explicitly mentions CLAUDE.md and warns against stale instructions; core example of system prompt persistence

AI Coding Agents in 2026: Claude Code, Cursor, and How We Actually Use Them | by Kevin Gabeci | Mar, 2026 | Medium example_of

Author explicitly references building a CLAUDE.md context file in previous work and describes it as core to their system. This is a direct instantiation of context engineering best practice.

Claude Code: CLI tooling and plan mode transformed my workflow | Anand Sainath posted on the topic | LinkedIn example_of

Article explicitly discusses CLAUDE.md as persistent context layer that survives session resets

Context Engineering for AI Agents in Open-Source Software - arXiv example_of

Paper explicitly mentions CLAUDE.md and AGENTS.md as vendor-recommended patterns for maintaining context in version control

10 Claude Code Tips That Will Change How You Code (2026) example_of

Article title explicitly mentions 'CLAUDE.md project memory' as tip #1 or major element. This is a direct application of the CLAUDE.md context engineering pattern.

@aibuilderclub_: Most builders run one AI coding agent at a time. example_of

Each agent receives a CLAUDE.md with task specification—direct application of per-agent context engineering

Build with Agent Skills extends

SKILL.md + references/ structure parallels CLAUDE.md approach of encoding system context, but scales it to portable, composable instruction sets. Each skill ships its own metadata plus supporting mate

query this concept

$ db.articles("claudemd-pattern")

$ db.cooccurrence("claudemd-pattern")

$ db.contradictions("claudemd-pattern")