martin1847/evolab / skills/agent-backend-standard
agent-backend-standard
Verified后端架构与工程规范。适用于构建或评审 agent/LLM 后端、任何涉及数据库(DB)的后端,以及建立或评审后端仓库工程门禁。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.5 KB |
| references/agent-foundations.md | markdown | 2.3 KB |
| references/caching-discipline.md | markdown | 3.9 KB |
| references/code-dependency-lifecycle.md | markdown | 9.5 KB |
| references/data-write-discipline.md | markdown | 9.9 KB |
| references/engineering-interface.md | markdown | 10.9 KB |
| references/evals.md | markdown | 2.6 KB |
| references/governance.md | markdown | 2.7 KB |
| references/hitl-resume-safety.md | markdown | 2.7 KB |
| references/observability-cost.md | markdown | 1.2 KB |
| references/prompt-context.md | markdown | 1.6 KB |
| references/resilience.md | markdown | 3.9 KB |
| references/safety-bounded-execution.md | markdown | 4.5 KB |
| references/secrets-discipline.md | markdown | 2.5 KB |
| references/selfcheck-gates.md | markdown | 4.4 KB |
| references/state-durability.md | markdown | 2.6 KB |
| references/tool-design.md | markdown | 2.8 KB |
references/observability-cost.md
View on GitHub# III-11 — 可观测与成本 / 时延
> hub `agent-backend-standard` 的一章(**薄**)。埋点本体不在此——canonical 在独立 skill `observability-standard`(粒度规则:埋点是不同触发动词,独立 skill)。本章只加 agent 特有的**成本 / token / 时延**面 + 指回 observability。
## 1. 交叉引用(不重复)
- trace_id 串 trace/log、结构化日志、OTel、GenAI 语义约定、honest span(`ok=False`+`error_type`)、脱敏维度 → **`observability-standard`**。II-9 的诚实 span 要求亦锚那里。
## 2. 成本 / token / 时延(本章 MUST)
- **每任务记 token + 美元成本**(prompt/completion 分项)、**端到端时延**、每步 LLM/工具耗时;脱敏。
- **预算上限**:每任务 / 每租户设 token·成本上限,超则停 + 上报(呼应 II-7 退出条件、II-9 失控防护)。
- **告警 / 看板**:p95 时延、成本异常、超时率、`cancelled` 率。
- eval 驱动选型也看成本(见 III-10 *TBD*):同质量挑更省的模型。
## 一句话
> 埋点走 `observability-standard`;本章只管 agent 的钱和时间——每任务记 token/成本/时延、设预算上限超则停、对 p95 与成本异常告警。
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |