Synchronize AGENTS.md files to CLAUDE.md recursively, adding CLAUDE.md to .gitignore, so Claude Code automatically reads the same instructions that other AI tools use.
A Claude Code plugin that syncs AGENTS.md → CLAUDE.md recursively across your entire project tree.
AGENTS.md files in your projectCLAUDE.md in the same directoryCLAUDE.md to .gitignore (if not already present)Some tools and workflows standardise on AGENTS.md for agent instructions. Claude Code reads CLAUDE.md. This plugin keeps them in sync transparently.
/plugin marketplace add intellectronica/claude-agentsmd
/plugin install claude-agentsmd@intellectronica-claude-agentsmd
Then restart Claude Code.
Uses SessionStart and UserPromptSubmit hooks that run a shell script. The script:
finds all AGENTS.md files (excluding .git/)cps each to a sibling CLAUDE.mdCLAUDE.md is in .gitignore<claudeMd> tags, which Claude Code injects directly into contextThe hooks have a 10-second timeout.
bash, find, cp, grep (standard on macOS and Linux)CC0 1.0 Universal
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub intellectronica/claude-agentsmd --plugin claude-agentsmdAutomatically detects and loads AGENTS.md files to provide agent-specific instructions alongside CLAUDE.md. Enables specialized agent behaviors without manual intervention.
CLAUDE.md lifecycle toolkit: initialise, enhance, sync, and modularise CLAUDE.md files with a 150-line cap, automatic chaining, and Karpathy behavioural guardrails.
Generate and maintain AGENTS.md, copilot-instructions.md, and other agent rule files
Intelligent sync of Claude instructions with enforcement hooks for security and consistency
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Memory compression system for Claude Code - persist context across sessions