agentacct-workflow

# agentacct Workflow ## Overview Use agentacct as a lightweight workflow ledger for AI-agent work. When the agentacct MCP tools are available, record a compact timeline of meaningful work rather than relying only on final chat summaries. This skill does not mean agentacct automatically sees every token or exact provider bill. MCP events, local usage imports, and provider/proxy cost enforcement are separate capabilities. ## When to Use Use this skill when: - Working in a repository that has agentacct initialized. - agentacct MCP tools such as `agentacct_record_event` are available. - Running Hermes, OpenCode, OpenClaw, Claude Code, Codex, or another coding agent with agentacct integration. - The user asks for evidence of AI-agent work, token/cost tracking, MCP smoke tests, or Agent FinOps workflow validation. Do not use this skill to claim exact billing unless the run used a supported usage importer or provider/proxy path. ## Workflow 1. If local client identifiers are available, call `agentacct_attach_client_context`: ```text source: hermes or the active coding-agent name client: hermes, claude-code, codex, opencode, openclaw, or other client_session_id: local session/thread id client_transcript_id: local transcript/log id if known parent_client_session_id: parent/root session id if this is a child agent turn_id/message_id/request_id: current ids if known client_event_timestamp: client timestamp if known ``` 2. Before meaningful work, open a section with `agentacct...