ワンクリックで
mechanic-safety-boundaries
Hard limits on Mechanic operations. These cannot be overridden by task directives.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Hard limits on Mechanic operations. These cannot be overridden by task directives.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Detect and prevent product-specific terminology contamination across skills/ and prompts/. Run after any bulk content update, skill import from another project, or agent config change. Applied as a shared skill across all agents.
When and how Architect delegates tasks to AO, Mechanic, and Designer.
Checklist and rules for reviewing deployment requests. Architect assesses but NEVER executes.
Rules for triaging new issues, classifying severity, and routing to the correct agent.
How to classify and respond to CI/pipeline failures.
Rules for detecting and managing stale issues and PR reviews.
| name | mechanic-safety-boundaries |
| description | Hard limits on Mechanic operations. These cannot be overridden by task directives. |
| metadata | {"version":"1.0.0","type":"policy"} |
mechanic:task_completed with:
files_modified: list of files changedfiles_count: number of files changedoperation_type: which whitelist categorybranch: branch namepr_number: if PR was created/updatedmechanic:task_failed with:
reason: one of [outside_whitelist, complex_conflict, ambiguous_task, scope_exceeded, escalation_required]detail: human-readable explanationoriginal_task: the task that was requested