Generates safety checklists with risk and result tracking for destructive actions.
npx skills add https://github.com/softwaresalt/csv-managed --skill safety-modes
Please help me install this Agent Skill. Skill: safety-modes Source: https://github.com/softwaresalt/csv-managed/tree/main/.github/skills/safety-modes Command: npx skills add https://github.com/softwaresalt/csv-managed --skill safety-modes
It reduces the chance of unintended damage by forcing elevated-risk work into an explicit, operator-visible safety workflow before anything risky happens.
careful, freeze-scope, and investigate-first to match different risk profiles and uncertainty levels.ActionRisk and an ActionResult lifecycle (planned, blocked, approved, applied, rolled-back, abandoned).freeze-scope, constrains edits to an allowed boundary and includes lock-conflict verification for boundary files to prevent contention-related failures.investigate-first, separates evidence from assumptions and blocks fixes until hypotheses are explicit and testable.Enter the requested mode for your current work session by asking the agent to produce a safety checklist for the risky task you intend to perform, including proposed actions with ActionRisk and ActionResult.
High-intent search queries and answers about installing and using this skill.
To prevent accidental destructive actions, an explicit safety checklist tracks each risky step with ActionRisk and an ActionResult lifecycle. This workflow enforces mode-specific protocols including approval gating and lock-conflict checks before destructive commands are applied.
The best way to enforce an approval workflow for large refactors is applying a careful mode safety protocol that requires explicit approval for boundary-sensitive changes. This ensures destructive actions are blocked without recorded explicit approval, treating the checklist as a strict-safety decision gate.
To contain uncertain root-cause debugging to a specific scope, use an investigate-first mode that separates evidence from assumptions. This protocol blocks fixes until hypotheses are explicit and testable, ensuring operator-visible safety during boundary-sensitive changes.
Yes, you can use freeze-scope boundary checks to prevent contention-related failures. Freeze-scope enforcement constrains edits to an allowed boundary and includes lock-conflict verification for boundary files, ensuring risky actions remain contained to a verified scope.
Yes, strict-safety decision-gate compliance halts operations on policy violations. When enabled, it treats the safety checklist as a decision gate and prevents destructive actions without recorded explicit approval, stopping execution if approval requirements are unmet.
tamaguiEnforce safe Git operations by blocking destructive commands during push, reset, and cleanup workflows.
idealic-aiRetrieve completed Gemini Deep Research results and update original requests.
tropeksRestrict Edit and Write operations to a specified directory using a Bash pre-tool hook.
maruakshayAssess multimodal systems for OCR prompt injection and vision-language vulnerabilities.