The Agent Skills Directory

[SAFE]: The skill does not contain any malicious code, obfuscation, or unauthorized data access patterns. Its primary purpose is to teach the configuration of local security and workflow hooks.
[COMMAND_EXECUTION]: Provides shell script templates that use common utilities like jq and grep to inspect tool inputs. These scripts are intended to be executed locally by the user's agent to enforce development policies.
[EXTERNAL_DOWNLOADS]: Includes a recipe for auto-linting that references npx prettier. This utilizes the official npm registry, a well-known service, to ensure code formatting consistency.
[DATA_EXFILTRATION]: Includes an audit logging recipe that writes tool metadata (timestamps, tool names, session IDs) to the local filesystem at ~/.claude/logs/. No network exfiltration or transmission of sensitive data was detected.

hooks-designer