agent-mail
Agent Mail is a Codex-native operator skill for managing file leases, system notifications, inboxes, and conflict prevention across distributed agent operations. Use it when coordinating multiple agents working with shared files, need to prevent simultaneous access conflicts, send notifications between agents, or maintain durable task state through a message-based side channel integrated with local shell operations.
git clone --depth 1 https://github.com/boshu2/agentops /tmp/agent-mail && cp -r /tmp/agent-mail/skills-codex/agent-mail ~/.claude/skills/agent-mailSKILL.md
# agent-mail (Codex) Codex-native entry point for the `agent-mail` operator skill. The AgentOps source skill `../../skills/agent-mail/SKILL.md` is the source of truth for domain behavior, commands, examples, references, and output expectations. Read it first, then use `prompt.md` for the Codex runtime profile. ## Codex Runtime Contract - Use Codex plus the local shell. Do not invoke Claude Code as an executor. - Load only the relevant source references or scripts for the task. - Prefer robot/JSON/NDJSON command surfaces when the source skill exposes them. - Keep durable task state, evidence, and closure in BR/beads; use Agent Mail as the side channel for leases and pings. - Verify command syntax from local `--help` or checked-in references before acting. - Return concrete evidence: commands run, files touched, exit codes, and any remaining blocker.
>-
>-
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.
>-