cyxj-deeper

cyxj-deeper is a skill for Claude Code, Codex from chenyuxiaojin/xiaochen-skills. It costs 196 tokens per session (1,501 once invoked), scanned A, original, MIT.

A task-planning method that first asks four questions about the goal, source material, methods, and outside evidence. It then rewrites the task into a deeper version and waits for approval before acting.

In plain words
What is it for?
It is for making video, writing, design, research, or tool-building requests more rigorous before execution.
Why use it?
It prevents an agent from rushing into a shallow solution or expanding the task without a clear reason and way to judge the result.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for making video, writing, design, research, or tool-building requests more rigorous before execution.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chenyuxiaojin/xiaochen-skills/cyxj-deeper
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 chenyuxiaojin/xiaochen-skills --skill cyxj-deeper
Clone the repo
git clone --depth 1 https://github.com/chenyuxiaojin/xiaochen-skills

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin cyxj-deeper — /plugin install cyxj-deeper after adding the marketplace above.

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 cyxj-deeper

README.md
[![agentmods](https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-deeper/github.svg)](https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-deeper)
Your own site
<a href="https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-deeper"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-deeper/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 cyxj-deeper

Your own site · 80×15
<a href="https://agentmods.dev/skills/chenyuxiaojin/xiaochen-skills/cyxj-deeper"><img src="https://agentmods.dev/badge/skills/chenyuxiaojin/xiaochen-skills/cyxj-deeper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 196 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,501 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 $0.00196 $0.01501
Opus 5.5 $0.00078 $0.00600
Sonnet 5.5 $0.00039 $0.00300
Haiku 4.5 $0.00020 $0.00150

Measured 5d ago against content hash 8ced048f8a8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cyxj-deeper 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 5d 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.

plugins/cyxj-deeper/skills/cyxj-deeper/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cyxj-deeper · 做深,不做大

方法论来自 Felix Rieseberg《How to be more ambitious: A tutorial for humans with models》 (https://felixrieseberg.com/how-to-be-more-ambitious-a-tutorial-for-humans-with-models/ ,2026-10-13): 模型的能力早已远超大多数人的用法,真正的瓶颈是人不敢要。这个 skill 的任务是替用户把要求往深处提—— 不是加更多功能、更多页数,而是做成这个领域顶尖的人会交出的那个版本。

用户是非程序员——解释直白,术语第一次出现就一句话说清。

流程(三步,顺序执行)

第 1 步:四问(动手前必须答完)

先从对话上下文、项目文件、~/项目/内容创作/log/index.md 推断任务背景,推断得出来的不许再问。然后逐条回答:

  1. 顶尖的人会多做什么:这个领域顶尖的从业者/创作者,在这里会多做哪些用户没要求的事?
  2. 最原始的材料:他们会从哪种最原始的材料起步——后台数据、评论区、原片素材、一手来源、原始数据—— 而不是别人已经消化过的二手总结?
  3. 具体方法和工具:他们会用哪些具体方法和工具?要真的去用(跑数据、做对照、写脚本、抽帧), 不是只换一套专家口吻。
  4. 外部裁判:除了模型和用户之外,什么能证明结果是对的?平台数据、可自动跑的检查脚本、对照样本、 真实观众反馈。不许模型给自己打分。

涉及外部事实(平台规则、工具能力、行业做法)要联网查证,查不到就标「未验证」,不许拿记忆冒充事实。

第 2 步:重写任务,给用户确认

把原任务重写成深度版,格式:

## 结论(一句话:深度版要交付的结果,用动词定义)

## 四问
1. 顶尖的人会多做:……
2. 起步材料:……(在哪、能不能拿到)
3. 方法和工具:……
4. 外部裁判:……(怎么判对错,谁来判)

## 重写后的任务
(一段可以直接执行的需求)

## 需要你拍板的
(只列答案会改变做法的 1~3 个决定)

然后停下等用户确认。用户说「行/开干」才进入第 3 步;用户改了就按改的来。

第 3 步:执行

按确认后的深度版执行。过程中遇到「做不到」先别退回原版——换方法再试;真卡住了,说清卡在哪、 已经试过什么,再请用户决定。交付时附上第 4 问的外部裁判结果(数据、脚本输出、对照),而不是自评。

原则(来自原文)

  • 定结果,不派单任务。 问一句「目标背后的目标是什么」:不是「修这个崩溃」,是「保证 app 不崩」; 不是「改这篇稿」,是「这条视频在某平台达到某个数据」。前提是让模型自己能拿到反馈、能复现、能验证。
  • 用专家的方法,而不是专家的用词。 想用 markdown 表格糊弄的地方,坚持上数据库、统计、对照实验。
  • 敢定不合理的目标,并当作合理去推。 网页 10 秒加载,就直接要 200 毫秒;模型说做不到,告诉它能做到,让它继续。
  • 用外部裁判。 结果由数据、脚本、样本来判,不由模型或用户的感觉来判。
  • 用动词定义作品。 季度汇报不是「一份 PPT」,是「30 分钟内让忙碌的人信服一个因果故事」; 一条视频不是「一个 3 分钟成片」,是「前 5 秒让刷到的人觉得这事和他有关」。
  • 组专家队伍,但做他们会做的事,不角色扮演。 编剧去拆结构、剪辑去看节奏、音频设计去测响度、 红队观众去找划走点——每个角色交付他那一行真正会交付的东西,而不是模仿他的口气说话。

原文深度 prompt(原样保留)

I want a deeper version of this task, not a bigger one. Before rewriting it: (1) say what a top professional in this field would do here that I'm not asking for; (2) name the rawest material they would start from instead of what has already been digested for me; (3) name the specific methods and tools they would use; (4) say what, other than you or me, would show the result is right. Then rewrite my prompt to ask for exactly that.

Read the full file on GitHub · 90 lines

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. 5d ago First seen · 90 lines · 196 tokens per session scan A 8ced048f8a8f

Subscribe to this mod's changes

cyxj-deeper is a skill published in the GitHub repository chenyuxiaojin/xiaochen-skills (8 stars, last pushed 5d ago), licensed MIT. It adds 196 tokens to every session and 1,501 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-10-20.

Related

Other skills, from other repositories

triage

Work a repo's needs-triage backlog, and outside contributors' issues and pull requests, in batches the decider approves in one pass: each item gets a cheap check and one proposed move with a plain-words reason, and only approved moves are applied. Use when asked to triage or work through a needs-triage pile, or to…

timharris707/skills · 83 tokens

retro

Read a sample of one repo's past agent sessions, Claude Code and Codex, find the friction the agents hit, and return a short ranked list of fixes in plain words, each labeled and routed to whoever owns the fix. Use when the user asks for a retro or retrospective on agent work, asks what keeps going wrong in a repo's…

timharris707/skills · 83 tokens

ingest

For a media file or URL shared with a goal, transcription requests, or takeaways from a call, demo, playtest, or video, build a transcript and timestamped visual evidence packet with a manifest and recommended next workflow.

timharris707/skills · 49 tokens

show-me-your-work

For autonomous multi-phase or unattended work, a reviewer needing an evidence trail, or an explicit decision-log/show-your-work request, keep an append-only decision log with why, evidence, and result. Record decisions and corrections, not hidden reasoning transcripts.

timharris707/skills · 54 tokens

to-tickets

When asked to file tickets, break down approved work, or move a settled plan onto the board, turn the spec, closed decision map, or pressure-tested conversation into verifiable work items with real dependencies and non-ticket blockers.

timharris707/skills · 49 tokens

setup

For a new TeamWorkflow installation, binding refresh, or drift audit after a pack release, inspect and bind the project workflow. Reuse explicit recorded decisions with their sources; ask about missing, conflicting, or changed authority and bindings.

timharris707/skills · 48 tokens