菜单
Records every agent execution turn as a run in Mission Control. Use this skill when starting a run (status RUNNING), completing or failing one (COMPLETED / FAILED), and reporting model, token counts, and cost so the observability and audit trail stays honest across all agent activity.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/jaydubya818/MissionControl --skill mission-control-run-logging命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Umbrella skill for integrating an agent with Mission Control, the orchestration and observability control plane. Use this skill when an agent needs to interact with Mission Control and you must route to the right focused skill — registration, heartbeats, task lifecycle, approvals, deliverables, memory, budget, or run logging. All interactions use Convex mutations and queries; there is no REST API.
Use this skill when a Mission Control work item is complete or awaiting review and an operator needs a factual handoff draft with outcome, evidence, unresolved risk, next owner, and next action.
Tracks and enforces agent spend in Mission Control. Use this skill when recording costs via api.agents.recordSpend, declaring budgetDaily and budgetPerRun limits at registration, or reacting to budgetRemaining and budgetExceeded values returned by the heartbeat before spending more money.
| name | mission-control-run-logging |
| description | Records every agent execution turn as a run in Mission Control. Use this skill when starting a run (status RUNNING), completing or failing one (COMPLETED / FAILED), and reporting model, token counts, and cost so the observability and audit trail stays honest across all agent activity. |
| version | 1.0.0 |
| owner | software-factory |
| risk | low |
| capabilities | ["run-recording","token-accounting","audit-trail"] |
| requires_tools | ["convex"] |
| related_skills | ["mission-control-budget-control","mission-control-heartbeat"] |
Record each execution turn:
Mutation: api.runs.create
Args:
agentId: Id<"agents">
taskId?: Id<"tasks">
sessionKey: string
model: string — e.g., "claude-sonnet-4-20250514"
inputTokens: number
outputTokens: number
costUsd: number
status: "RUNNING" | "COMPLETED" | "FAILED"
idempotencyKey: string
status: "RUNNING", then record the terminal state (COMPLETED or FAILED) with final token counts and cost.idempotencyKey so retried creates never duplicate run records.costUsd through to spend tracking as well (mission-control-budget-control).
基于 SOC 职业分类