Practices
Guard hooks for agents
Scripts that run before or after an agent's tool calls to block or flag risky actions.
ADOPTOn the radar since 12 Oct 2026Draft
Why Adopt
Hooks check commands, file reads and email sends before they run, and the agent cannot switch them off.
Movement
On other radars
No community radar places this yet.
Sources
- Claude Code documents hooks that run on tool calls and other events. checked 12 Oct 2026
Also in Practices · Adopt
- Agent skillsPackaged instructions and scripts that an agent loads when a task matches them.
- AGENTS.md instruction filesA plain Markdown file that tells coding agents how to work in a repository.
- Ask-first gateLetting agents ship work end to end while a short list of change types waits for the owner's approval.
- Company brainKeeping a company's strategy, decisions and facts in documents that agents read before they act.
- Model tier per taskAssigning each agent task to the smallest model that can do it reliably.
- Parallel agents in worktreesRunning several coding agents at once, each in its own git worktree and its own context.