zhihu-answer

zhihu-answer is a skill for Claude Code from hanmirage/deepdepcat. It costs 50 tokens per session (291 once invoked), scanned A, original, Apache-2.0.

A writing template for Zhihu, a Chinese question-and-answer platform. It organizes answers around an early conclusion, layered reasoning, evidence, sources and limits.

In plain words
What is it for?
Use it to draft structured Zhihu answers with conclusions, arguments, data, citations and optional follow-up questions.
Why use it?
It prevents long answers from burying the main point or making unsupported claims. It also reminds the writer to explain when a conclusion does or does not apply.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to draft structured Zhihu answers with conclusions, arguments, data, citations and optional follow-up questions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hanmirage/deepdepcat/zhihu-answer
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 hanmirage/deepdepcat --skill zhihu-answer
Clone the repo
git clone --depth 1 https://github.com/hanmirage/deepdepcat

Made for: Claude Code.

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 zhihu-answer

README.md
[![agentmods](https://agentmods.dev/badge/skills/hanmirage/deepdepcat/zhihu-answer/github.svg)](https://agentmods.dev/skills/hanmirage/deepdepcat/zhihu-answer)
Your own site
<a href="https://agentmods.dev/skills/hanmirage/deepdepcat/zhihu-answer"><img src="https://agentmods.dev/badge/skills/hanmirage/deepdepcat/zhihu-answer/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 zhihu-answer

Your own site · 80×15
<a href="https://agentmods.dev/skills/hanmirage/deepdepcat/zhihu-answer"><img src="https://agentmods.dev/badge/skills/hanmirage/deepdepcat/zhihu-answer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 291 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 $0.00050 $0.00291
Opus 5 $0.00025 $0.00146
Sonnet 5 $0.00010 $0.00058
Haiku 4.5 $0.00005 $0.00029

Measured 9d ago against content hash 87644c812180, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

zhihu-answer 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.

.deepdepcat/skills/zhihu-answer/SKILL.md · 24 lines

What it actually says

知乎回答模板

结构

  • 前置结论:第一段直接给答案(3 句内),不铺垫;
  • 论证分层:按「是什么 → 为什么 → 怎么做」或「证据 → 解释 → 边界」组织;
  • 引用与数据:每个关键论断带来源;无法查证的标注「未证实」;
  • 边界说明:说明结论适用的前提与不适用的情况;
  • 结尾:一句总结 + 一个延伸问题(可选)。

要求

  • 段落 ≤ 6 行,小标题按需使用;
  • 不写「谢邀」式套话;语气专业但不端着;
  • 长回答可导出 docx_generate
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 · 24 lines · 50 tokens per session scan A 87644c812180

Subscribe to this mod's changes

zhihu-answer is a skill published in the GitHub repository hanmirage/deepdepcat (10 stars, last pushed 20d ago), licensed Apache-2.0. It adds 50 tokens to every session and 291 once invoked, about $0.0003 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.