Skip to content

fix: restore missing setup-claude-hooks.sh (regression from PR #33)#61

Open
reshadat wants to merge 1 commit into
rinadelph:mainfrom
reshadat:fix/restore-setup-claude-hooks-regression
Open

fix: restore missing setup-claude-hooks.sh (regression from PR #33)#61
reshadat wants to merge 1 commit into
rinadelph:mainfrom
reshadat:fix/restore-setup-claude-hooks-regression

Conversation

@reshadat

Copy link
Copy Markdown

Problem

setup-claude-hooks.sh is referenced throughout the documentation but is missing from the repository, preventing users from setting up multi-agent file locking (issue #50).

This is a regression from PR #33, which added the script but it was subsequently lost from the main branch.

Fix

Restores the original setup-claude-hooks.sh script from PR #33 history. The script:

  • Creates .claude/settings.json with PreToolUse file-lock hooks to prevent multi-agent conflicts
  • Configures PostToolUse activity broadcasting
  • Verifies required hook files exist before proceeding
  • Creates .agent-locks and .agent-activity directories

Testing

git clone https://github.com/rinadelph/Agent-MCP.git
cd Agent-MCP
uv venv && uv pip install -e .
./setup-claude-hooks.sh
# Expected: "Claude Code hooks configured successfully!"

Closes #50

…lph#33)

The setup-claude-hooks.sh script was added in PR rinadelph#33 to configure Claude Code
hooks for multi-agent file locking, but was subsequently lost from the main branch.

This restore fixes issue rinadelph#50 by bringing back the original script that:
- Creates .claude/settings.json with PreToolUse file-lock hooks
- Configures PostToolUse activity broadcasting
- Verifies required hook files exist before proceeding
- Sets up .agent-locks and .agent-activity directories

Closes rinadelph#50
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.

setup-claude-hooks.sh script missing despite being referenced in documentation (regression from PR #33)

1 participant