OpenAI 工程维护 Prompts（原文）

---

来源

原文：Maintaining software with the GPT-6 family。

作者：Rodrigo Roim · OpenAI Developers · 2026 年 10 月 14 日。

以下收录文章公开展示的六组英文 Prompt，仅作分节与代码块排版，不扩写指令。第 3 组保留原文的 [Omitted for brevity: ...] 说明，未补写被省略的内容。

1. Removing unused code — 清理无用代码

Can you help identify and clean up dead code in the repo please, feel free to check slack,
statsig [a feature flag and experimentation platform we use], or any other source you need to
confirm that things are indeed no longer being used and can be cleaned up or simplified

2. Tracking down stale experiments — 清理过期实验

Find and remove substantial dead code associated with stale, constant Statsig gates/configs or
abandoned experiments in projects {A} and {B}. Verify live Statsig configuration and check git
history and overlapping PRs. Preserve production behavior, operational safeguards and
gates/configs intended as killswitches or similar. Ignore SDK fallbacks and local overrides.
Create one small draft PR per cleanup, linking its Statsig configuration console link in the
summary.

3. Repository-wide Statsig audit — 全仓库实验配置审计

/goal Find every stale, constant, abandoned, or fully shipped Statsig gate, config, experiment,
and layer present in this entire repository that can safely be removed with no production
changes. Audit all Statsig projects and inventories, not just objects labeled stale.
Find indirect usages through enums, constants, wrappers, aliases, schemas, dynamically assembled
names, and cross-service consumers. Reconcile every production-referenced constant; do not stop
after producing a conservative shortlist.
Consider each object's cloud resource usage, including CPU. Use production telemetry and
profiles where available to identify expensive dead checks.
[Omitted for brevity: detailed instructions, generated by Astra, on verifying production
behavior, prioritizing older objects, preserving intentional safeguards, and interpreting SDK
fallbacks.]
Produce a markdown report grouping all verified candidates into parallelizable ownership/file
workstreams, including production values, evidence, owners, callsites, and observed evaluation
or CPU costs if available.
Do not modify live configurations or services.

4. Fixing flaky tests — 修复不稳定测试

/goal Look at all recent CI runs to find flaky tests. For each flaky test, try a fix and if
successful put up a PR. Your job is to find clear fixes to simple issues, not to exhaustively
fix every flaky test.

5. Improving agentic context — 改进 Agent 指令

Look through my recent Codex sessions and find one AGENTS.md instruction that appears to have
misdirected an agent or caused unnecessary work. Choose the original session prompt where that
happened. Replay that same prompt twice from the same repository snapshot and model:
1. With the current AGENTS.md instruction unchanged.
2. With only that one instruction removed or fixed.

Compare task quality, agent behavior, tool calls, token usage, runtime, and cost. Show the
instruction and whether updating it helped.

6. Reducing CI cost and runtime — 降低 CI 成本与耗时

What ideas do you have to relieve CI load in this repository? List your ideas in a table and
rank all of them by estimated CI minutes saved per day based on this repo's CI run history

原始出处

OpenAI — Maintaining software with the GPT-6 family