process-triage
Process-triage provides diagnostic tools for identifying and safely managing runaway processes through the `pt` command wrapper. Use it when system processes consume excessive resources and you need structured analysis before termination, relying on `pt scan`, `pt deep-scan`, and `pt agent` subcommands to assess process behavior and recommend remediation steps that require explicit user approval before execution.
git clone --depth 1 https://github.com/boshu2/agentops /tmp/process-triage && cp -r /tmp/process-triage/images/gemini/skills/process-triage ~/.claude/skills/process-triageSKILL.md
# process-triage Use `pt` as the user-facing command and `pt help` for wrapper-aware help. Core workflows: - `pt scan --format json` - `pt deep-scan --format json` - `pt agent plan` - `pt agent explain` - `pt agent apply` Safety: - Never kill automatically without explicit user approval - Prefer `pt agent` over legacy `pt robot` - Use structured output for agent automation
Use Agent Mail from Codex for file leases, notifications, inboxes, and conflict prevention.
>-
>-
Use when converting markdown plans into br beads with dependencies for implementation or swarm execution.
Use when switching AI coding CLI accounts quickly to recover from subscription rate limits or OAuth friction.
>-
Use when starting non-trivial work, mining lessons, or preventing repeated mistakes with cm procedural memory.
Mine past agent sessions for working prompts, decisions, and patterns. Use when "what did I ask?", "find that prompt", session archaeology, or agent history.