one-by-one

one-by-one is a skill for Codex from BackToCimaCoppi/Praxis. It costs 120 tokens per session (1,899 once invoked), scanned A, original, Apache-2.0.

A conversation mode that handles decisions one question at a time in plain Chinese, records each answer, and then moves to the next question.

In plain words
What is it for?
Use it after cancelling a question dialog, when an explanation is unclear, or when you want to discuss several technical decisions separately.
Why use it?
It helps when a batch of questions or a pop-up is hard to follow, especially in a terminal, desktop app, or development tool.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: names the AskUserQuestion tool; mentions Claude Code.

Good fit Use it after cancelling a question dialog, when an explanation is unclear, or when you want to discuss several technical decisions separately.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/backtocimacoppi/praxis/one-by-one
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.

Any agent
npx skills add BackToCimaCoppi/Praxis --skill one-by-one
Clone the repo
git clone --depth 1 https://github.com/BackToCimaCoppi/Praxis

Made for: Codex.

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 one-by-one

README.md
[![agentmods](https://agentmods.dev/badge/skills/backtocimacoppi/praxis/one-by-one/github.svg)](https://agentmods.dev/skills/backtocimacoppi/praxis/one-by-one)
Your own site
<a href="https://agentmods.dev/skills/backtocimacoppi/praxis/one-by-one"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/one-by-one/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for one-by-one

Your own site · 80×15
<a href="https://agentmods.dev/skills/backtocimacoppi/praxis/one-by-one"><img src="https://agentmods.dev/badge/skills/backtocimacoppi/praxis/one-by-one.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,899 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00120 $0.01899
Opus 5 $0.00060 $0.00949
Sonnet 5 $0.00024 $0.00380
Haiku 4.5 $0.00012 $0.00190

Measured 9d ago against content hash 226af1506d87, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

one-by-one 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 9d 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.

skills/one-by-one/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

one-by-one:逐题裁决模式

一句话:用户要裁决多件事时,不弹窗,用通俗汉语一次讲一题,裁一题、落盘一题,再进下一题。

为什么存在:弹窗式提问在 CLI / 桌面 / IDE 插件多端存在遮挡 bug(弹窗盖住上方解释文字,用户被迫盲选);批量抛问题加 AI 式表达会把重点淹没。本 skill 只固定「怎么问、怎么记」;问什么、问几个仍由原流程决定——总控、lightweight-designadversarial-reviewplan-goal 等流程的实质步骤与问题内容不受影响。

0. 触发纪律

  • 仅用户输入 /one-by-one 触发;AI 永不主动激活(建议在 settings.json 用 skillOverrides 把本 skill 设为 user-invocable-only 兜底)。
  • 触发时先判断入口场景:
入口场景 第一步动作
用户刚取消了一个弹窗 把弹窗里那批问题按本模式重新提出
用户看不懂刚才的解释/提问 先按 §2 规范把刚才的内容重讲一遍,再进入逐题流程
预防性触发(裁决还没开始) 直接按 §1 流程开始
  • 生效范围:本会话余下全程,直到用户明说退出(如「恢复弹窗」「退出逐题模式」)。

1. 逐题流程

① 问题总览表:编号 + 一句话主题 + 状态(让用户先看到一共几件事)
② 每次只谈一题:按 §2 结构讲完,纯文本等用户裁决
③ 用户裁决 → 立即按 §3 落盘 → 展示记录原文 → 更新总览状态 → 下一题
④ 全部谈完 → 输出本轮裁决总表
  • 全程禁用弹窗式提问工具(Claude Code 的 AskUserQuestion);一切提问、追问、落点确认都用纯文本。
  • 等待裁决时,禁止假定某个选项成立而继续推进相关工作。
  • 用户答复含糊 → 允许追问,但追问同样一次只问一件事。
  • 用户主动一次裁决了多题 → 尊重,逐条落盘后继续;但 AI 不得主动把多题打包求一次总体同意。
  • 假决策处理(三分):①上游流程列出的决策点一律不吞——AI 论证为唯一解的照样出题,标注「已论证唯一解 + 理由」,用户一句话即可秒批;②AI 在本会话自造的题,讲不出「选 A 和选 B 用户会遇到什么不同」就不出题,在总览表正文列一行告知(不得放表下附注);③「答不出差异」不是吞题理由——那是背景不足,降级为「我没搞懂,请求补背景」。判定标准前后不一致(声称唯一解不占用用户、却又抛唯一解题)视为流程违规。

2. 每题结构与表达规范

每题固定四段,总长控制在一屏内:

要求
背景 1–2 句,只讲这道题必需的前情
分歧点 一句话说清到底在选什么
选项 每项一行:做法 + 代价/后果/不可逆性
推荐 明确推荐哪个 + 一两句理由

表达红线

  • 通俗汉语技术方案语言。面向资深工程师:技术概念不必降维,但必须说人话。
  • 表述海拔:标识符(类名/表名/字段名/方法名)只作锚点(每个论点至多一个),禁贴代码/伪代码,禁逐方法调用链复述。
  • 锚定:会话内部产生的名词(方案名、编号、新标签)默认用户不在场,首次出现必须带一句话锚点(它是什么 + 在哪 + 扮演什么角色)。本模式要求三点:①内部编号(DEC-x、T-x 等)首次引用就地展开,不许要求用户跳转查阅;②任务内新命名的标签/方案名——哪怕字面全由通用技术词构成(如"内容哈希""源指针")——必须锚定到具体对象:它作用于哪份数据、存在哪、谁消费它;通用技术概念本身仍零解释、零降维;③锚点每个至多半句、计入一屏预算,一屏放不下就拆题,不砍锚点、不破一屏。
  • 代价落地:选项的代价/后果必须写成用户可感知的结果(会看到什么不同、卡住什么动作)。有可靠依据时给数量级并注明出处;没有依据就写清可感知差异并明确标注「量级未知」,禁止编造数字。禁止只给实现层形容词("写入放大""成本最高")。
  • 禁 AI 自造黑话与八股。示例不穷举,同类都算:赋能、抓手、闭环、颗粒度、链路、心智、底层逻辑、护城河;「首先/其次/再次/综上所述」骨架。
  • 精简 ≠ 省略:影响裁决的细节(代价、风险、影响面、不可逆性)一个不漏;不影响裁决的过程叙述全部砍掉。
  • 试金石:用户不打开 IDE、不追问,能否直接拍板?不能 → 重写这道题。

3. 记录规则(防上下文压缩丢裁决)

落点优先级

  1. 当前任务已有 用户裁决记录.md → 追加 DEC-x(沿用既有编号序列)
  2. 正在编辑的方案/计划文档有「决策记录」节 → 追加该节
  3. 都没有 → 新建日期命名的记录文件,落点用纯文本问用户一次

Read the full file on GitHub · 91 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 91 lines · 120 tokens per session scan A 226af1506d87

Subscribe to this mod's changes

one-by-one is a skill published in the GitHub repository BackToCimaCoppi/Praxis (6 stars, last pushed 14d ago), licensed Apache-2.0. It adds 120 tokens to every session and 1,899 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

neurolink-guide

Guide for using the NeuroLink SDK and CLI. Invoke when users ask how to use neurolink, integrate AI providers, add MCP tools, configure RAG, set up memory, deploy servers, or work with multimodal content. Covers SDK, CLI, providers, tools, and enterprise features.

juspay/neurolink · 65 tokens

github-commenting

How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.

juspay/neurolink · 41 tokens

repo-conventions

NeuroLink's review standards — the critical rules to enforce, what NOT to comment on, the security bar, hot paths. Load before reviewing any change in this repository.

juspay/neurolink · 39 tokens

session-manager

A fallback skill for recording development sessions and restoring project context from an Obsidian vault, a folder of linked notes. It handles explicit resume, handoff, status, and end-of-session requests when automatic capture is unavailable.

Enakoneschniy/claude-dev-stack · 108 tokens

dev-research

A research workflow that uses NotebookLM, a tool for asking questions about a selected collection of documents, to answer development questions with citations.

Enakoneschniy/claude-dev-stack · 177 tokens

budget-continue

Show 4-option continuation prompt when session budget is low. Options: remind later (CronCreate), auto-continue locally (Desktop task), auto-continue in cloud (Cloud task), continue now. Trigger when: budget warning fires, session limit reached, context is full, user sees budget warning.

Enakoneschniy/claude-dev-stack · 64 tokens