Skip to content

Comments

feat(agents): add CLAUDE.md files to help claude code#1083

Merged
tengomucho merged 1 commit intomainfrom
claude.md-everywhere
Feb 20, 2026
Merged

feat(agents): add CLAUDE.md files to help claude code#1083
tengomucho merged 1 commit intomainfrom
claude.md-everywhere

Conversation

@tengomucho
Copy link
Collaborator

Some agents look for AGENTS.md, but claude code looks for CLAUDE.md and ignores AGENTS.md unless mentioned or imported. This change allows claude to research the information faster.

Some agents look for AGENTS.md, but claude code looks for CLAUDE.md and
ignores AGENTS.md unless mentioned or imported. This change allows
claude to research the information faster.
@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds CLAUDE.md entrypoints so Claude Code auto-loads existing AGENTS.md guides across key Optimum Neuron subdirectories, and documents the convention for future model additions.

Changes:

  • Add minimal CLAUDE.md files (importing @AGENTS.md) in vLLM, inference, and several model subdirectories.
  • Update optimum/neuron/models/inference/AGENTS.md with a “New Model Checklist” documenting the CLAUDE.md convention.
  • Update root AGENTS.md with “Context Loading” guidance.

Reviewed changes

Copilot reviewed 14 out of 14 changed files in this pull request and generated 2 comments.

Show a summary per file
File Description
optimum/neuron/vllm/CLAUDE.md Adds Claude entrypoint to load optimum/neuron/vllm/AGENTS.md.
optimum/neuron/models/inference/CLAUDE.md Adds Claude entrypoint to load optimum/neuron/models/inference/AGENTS.md.
optimum/neuron/models/inference/gemma3/CLAUDE.md Adds Claude entrypoint to load model-specific AGENTS.md.
optimum/neuron/models/inference/granite/CLAUDE.md Adds Claude entrypoint to load model-specific AGENTS.md.
optimum/neuron/models/inference/llama/CLAUDE.md Adds Claude entrypoint to load model-specific AGENTS.md.
optimum/neuron/models/inference/llama4/CLAUDE.md Adds Claude entrypoint to load model-specific AGENTS.md.
optimum/neuron/models/inference/mixtral/CLAUDE.md Adds Claude entrypoint to load model-specific AGENTS.md.
optimum/neuron/models/inference/phi3/CLAUDE.md Adds Claude entrypoint to load model-specific AGENTS.md.
optimum/neuron/models/inference/qwen2/CLAUDE.md Adds Claude entrypoint to load model-specific AGENTS.md.
optimum/neuron/models/inference/qwen3/CLAUDE.md Adds Claude entrypoint to load model-specific AGENTS.md.
optimum/neuron/models/inference/qwen3_moe/CLAUDE.md Adds Claude entrypoint to load model-specific AGENTS.md.
optimum/neuron/models/inference/smollm3/CLAUDE.md Adds Claude entrypoint to load model-specific AGENTS.md.
optimum/neuron/models/inference/AGENTS.md Documents adding CLAUDE.md when creating new model directories.
AGENTS.md Adds context-loading section (but currently contains a bad reference and confusing wording—see comments).

Comment on lines +14 to +16
- `optimum/neuron/models/inference/backend/modules/attention/AGENTS.md` — attention or NKI kernel work
- `optimum/neuron/models/inference/<model>/AGENTS.md` — model-specific work (gemma3, llama, qwen3, etc.)
- `optimum/neuron/vllm/AGENTS.md` — vLLM integration work
Copy link

Copilot AI Feb 20, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

optimum/neuron/models/inference/backend/modules/attention/AGENTS.md is referenced here, but that file does not exist in the repository (and the attention/ directory currently contains only Python sources). Please either add the referenced guide file or update/remove this bullet to point at the correct existing documentation path.

Suggested change
- `optimum/neuron/models/inference/backend/modules/attention/AGENTS.md` — attention or NKI kernel work
- `optimum/neuron/models/inference/<model>/AGENTS.md` — model-specific work (gemma3, llama, qwen3, etc.)
- `optimum/neuron/vllm/AGENTS.md` — vLLM integration work
- `optimum/neuron/vllm/AGENTS.md` — vLLM integration work
- `tools/cache/AGENTS.md` — cache tooling and shared cache infrastructure

Copilot uses AI. Check for mistakes.
@tengomucho tengomucho marked this pull request as ready for review February 20, 2026 16:09
@tengomucho tengomucho merged commit cfa36ba into main Feb 20, 2026
6 checks passed
@tengomucho tengomucho deleted the claude.md-everywhere branch February 20, 2026 16:46
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants