メニュー
Read OPC run artifacts and summarize token, API call, duration, and cost-related usage without invoking models or tools.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Produce a QA acceptance report for a task or change set following the acceptance-document field standard in docs/claude/standards.md.
Run a pre-QA implementation self-check against task scope, acceptance criteria, validation evidence, and pending diff.
Generate or append a task entry into tasks-pX.md following the task-list field standard defined in docs/claude/standards.md.
Produce a read-only release readiness recommendation from implementation results, QA evidence, environment details, and rollback conditions.
Read pending diff, PRs, task results, or selected files and produce a structured review without modifying code.
Convert a PRD, bug report, or task description into structured test points and targeted validation commands.
| name | token-report |
| description | Read OPC run artifacts and summarize token, API call, duration, and cost-related usage without invoking models or tools. |
只读分析 OPC run artifacts，基于 run_metrics.json、run_trace.json 和 run_events.jsonl 汇总 token、API 调用、耗时和成本相关字段；不得重新调用模型、工具或触发新的 workflow。
/token-report <latest run 或 artifacts 路径>
字段应优先直接对应 run_metrics.json 的现有或计划字段；字段缺失时标注为“缺失”：
| 字段 | 来源 | 输出要求 |
|---|---|---|
run_id | run_trace.json 或 artifacts 路径 | 标识本次 run |
input_tokens | run_metrics.json.totals.input_tokens | 输出总输入 token |
output_tokens | run_metrics.json.totals.output_tokens | 输出总输出 token |
api_calls | run_metrics.json.totals.api_calls | 输出 API 调用总数 |
duration_seconds | run_metrics.json.totals.duration_seconds | 输出总耗时 |
stage_usage | run_metrics.json.stages | 按 stage 列出 tokens、api_calls、duration、model、estimated_cost |
highest_usage_stage | stage_usage 派生 | 标出 token 或 cost 最高阶段 |
estimated_cost | run_metrics.json.totals.estimated_cost | 仅在 artifacts 已存在时输出 |
currency | run_metrics.json.totals.currency | 缺失时标注不适用 |
pricing_source | run_metrics.json.totals.pricing_source | 说明价格来源或缺失 |
anomalies | metrics/trace/events 对比 | 标记缺字段、异常耗时、异常调用数 |
optimization_suggestions | 分阶段消耗派生 | 给出证据驱动的优化建议 |
/token-report latest run/token-report artifacts/runs/20260526-120000/run_metrics.json[分析对象] latest / 指定 artifacts 路径
[读取 artifacts]
- run_metrics.json：存在 / 缺失
- run_trace.json：存在 / 缺失
- run_events.jsonl：存在 / 缺失
[总量]
- input_tokens：...
- output_tokens：...
- api_calls：...
- duration_seconds：...
- estimated_cost：...
- currency：...
- pricing_source：...
[分阶段消耗]
- stage：model / input_tokens / output_tokens / api_calls / duration_seconds / estimated_cost
[最高消耗阶段]
- token 最高：...
- cost 最高：...
[异常项]
- ...
[优化建议]
- ...
[结论] ...
[分析对象] ...
[读取 artifacts] run_metrics.json / run_trace.json / run_events.jsonl
[总量] input_tokens / output_tokens / api_calls / duration / estimated_cost / currency / pricing_source
[分阶段消耗]
- stage: model / input_tokens / output_tokens / api_calls / duration / estimated_cost
[最高消耗阶段] stage / 指标 / 数值
[异常项] ...
[优化建议] ...
[结论] ...