test-pre-flight

test-pre-flight is a command for coding agents from xcodethink/open-claude-code-skills. It costs 32 tokens per session (597 once invoked), scanned A, original, MIT.

A test mode for a conversation that turns everyday requests into precise instructions before serious work begins.

In plain words
What is it for?
Use it to test a five-step request-checking process, ask a small number of important questions, suggest a starting approach, and switch back to normal replies when finished.
Why use it?
It helps prevent an agent from misunderstanding a complex request or starting work before key decisions and constraints are clear.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/xcodethink/open-claude-code-skills/test-pre-flight
Clone the repo
git clone --depth 1 https://github.com/xcodethink/open-claude-code-skills

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for test-pre-flight

README.md
[![agentmods](https://agentmods.dev/badge/commands/xcodethink/open-claude-code-skills/test-pre-flight.svg)](https://agentmods.dev/commands/xcodethink/open-claude-code-skills/test-pre-flight)
Your own site
<a href="https://agentmods.dev/commands/xcodethink/open-claude-code-skills/test-pre-flight"><img src="https://agentmods.dev/badge/commands/xcodethink/open-claude-code-skills/test-pre-flight.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 597 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00032 $0.00597
Opus 5 $0.00016 $0.00298
Sonnet 5 $0.00006 $0.00119
Haiku 4.5 $0.00003 $0.00060

Measured 4d ago against content hash a04fa5b93216, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-pre-flight scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/test-pre-flight.md · 52 lines

What it actually says

test-pre-flight — 激活 Pre-Flight 测试模式

用户输入 /test-pre-flight 表示要在本对话里测试 Pre-Flight Check 协议的效果。

行为

立刻读取并完整加载: ~/.claude/prompts/lib/09-元指令/Pre-Flight协议.md

加载后告知用户:

✅ Pre-Flight 测试模式已激活。

从现在起,我会按以下方式处理你的请求:

1. 识别意图(严肃任务 vs 简单问答)
2. 严肃任务:静默挂载规范 + 记忆 + 项目档案 → 业务伙伴追问 → 起步方案 → 等你回应
3. 简单问答(解释/查询/typo):直接答,不 Pre-Flight

测试时长建议: 这次对话 + 接下来 1-2 周新对话(每次新对话开头 /test-pre-flight 激活)
退出: 说"退出 Pre-Flight 测试"或开新对话不激活
反馈渠道: 直接告诉我哪里别扭 / 哪里太啰嗦 / 哪里漏问

请告诉我你要做什么,我会按 Pre-Flight 方式回应。

关键约束

  • 加载后严格按 Pre-Flight 协议的 5 步流程执行,不允许偷懒
  • 简单问答跳过 Pre-Flight,不要每次都启动(避免烦)
  • 用普通话,禁止暴露 playbook 模板名("我加载了 stuck-bug" 错 → "我会先撤回之前的修改重新分析" 对)
  • 一次最多问 3-5 个最关键问题,不刷屏
  • 用户说"先做吧 / 别问"→ 简化为 1-2 个最关键问题
  • 用户说"退出 Pre-Flight 测试"→ 回到普通模式

测试目的

验证以下假设:

  • 我说人话 → AI 能精准翻译成执行指令
  • AI 主动追问比我自己想全面更省时间
  • 业务伙伴视角(不只是技术)能避免我返工
  • 严肃任务永远不会"AI 自由发挥跑偏"
  • 体验值得日常用,不嫌烦

不满足任一假设 → 反馈给我,迭代协议。

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 52 lines · 32 tokens per session scan A a04fa5b93216

Subscribe to this mod's changes

test-pre-flight is a command published in the GitHub repository xcodethink/open-claude-code-skills (2 stars, last pushed 29d ago), licensed MIT. It adds 32 tokens to every session and 597 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.