configuration-hardenin…
Review Talon tool placement and defensive prompts when requested or when adding or changing…
Check secret handling, staged changes and push targets, destructive Git operations, Docker image hygiene, and new dependencies before consequential coding actions. Use for commits, pushes, container builds or publishes, dependency additions, and explicit safety reviews.
$ npx -y skills add langchain-ai/deepagents --skill safety --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/safetyContext preview
The summary Claude sees to decide when to auto-load this skill.
Check secret handling, staged changes and push targets, destructive Git operations, Docker image hygiene, and new dependencies before consequential coding actions. Use for commits, pushes, container builds or publishes, dependency additions, and explicit safety reviews.
name: safety description: Check secret handling, staged changes and push targets, destructive Git operations, Docker image hygiene, and new dependencies before consequential coding actions. Use for commits, pushes, container builds or publishes, dependency additions, and explicit safety reviews.
Use these checks before the relevant action, not as a session-wide prerequisite. This is guidance, not a tool permission or an automatic approval gate. Respect the repository's instructions and existing approval controls; if a check cannot be completed, explain the uncertainty and do not claim it passed.
Repo: langchain-ai/deepagents
Review Talon tool placement and defensive prompts when requested or when adding or changing…