Block destructive commands and enforce per-directory edit boundaries.
npx skills add https://github.com/mr-daedalium/ostack --skill guard-mr-daedalium
Please help me install this Agent Skill. Skill: guard Source: https://github.com/mr-daedalium/ostack/tree/main/guard Command: npx skills add https://github.com/mr-daedalium/ostack --skill guard-mr-daedalium
Protects live environments from destructive commands and unintended edits by enforcing a directory-based edit boundary and warning before dangerous operations.
Use guard mode to set a freeze boundary for a target directory and enable destructive-command warnings.
High-intent search queries and answers about installing and using this skill.
To prevent destructive commands, this safety mode intercepts and blocks risky operations like rm -rf, DROP TABLE, and force-push before execution. It relies on hook scripts to warn you, protecting live systems during incident response, debugging, or sensitive deployments from unintended human error.
A directory-boundary restriction enforces a user-specified edit path to prevent accidental changes outside safe areas. By setting a freeze boundary, it restricts file modifications to a designated safe directory, protecting live environments from unintended edits during sensitive deployments.
Setting a freeze boundary involves activating guard mode to target a specific directory and enable destructive-command warnings. This configuration restricts all edits to the user-specified safe path, preventing accidental modifications to files outside the designated boundary during prod maintenance.
Yes, directory-boundary enforcement is ideal for safe-debug workflows during incident response and prod maintenance. It minimizes human error by restricting edits to a safe path and warning before dangerous operations, ensuring live server environments remain protected.
No external dependencies or components are required. The destructive command blocker relies entirely on internal /careful and /freeze hook scripts to perform checks, enforce directory boundaries, and block risky operations without needing additional installed packages.
The limitation of a per-directory edit boundary is that protection only applies within the specified freeze boundary path. Edits or destructive commands targeting areas outside the user-specified safe directory may not be intercepted by the hook scripts.
BaGyun0107Restrict file edits and writes to a configured directory boundary.
thejordanleopoldCodify CI/CD gates, canary monitoring, and rollback plans for safe deployments.
greencmMerge pull requests, run CI tests, and deploy to production with canary checks.
manuelbrandner85Generate minimal macOS Seatbelt sandbox configurations for process isolation.
