perplexity-improver

perplexity-improver is an agent for Claude Code from QQQingyu/story-snack. It costs 25 tokens per session (1,271 once invoked), scanned A, original, MIT.

A revision assistant that detects writing patterns often associated with AI-generated prose and rewrites the affected sentences. It also checks a project-specific list of unwanted words.

In plain words
What is it for?
Use it to scan a Chinese fiction draft, identify these patterns, and revise selected passages using the project’s rewriting guidelines.
Why use it?
It helps make a draft less predictable and avoids repetitive sentence structures, vague description, direct emotion labels, and explanatory endings.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to scan a Chinese fiction draft, identify these patterns, and revise selected passages using the project’s rewriting guidelines.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/qqqingyu/story-snack/perplexity-improver
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.

Clone the repo
git clone --depth 1 https://github.com/QQQingyu/story-snack

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 perplexity-improver

README.md
[![agentmods](https://agentmods.dev/badge/agents/qqqingyu/story-snack/perplexity-improver.svg)](https://agentmods.dev/agents/qqqingyu/story-snack/perplexity-improver)
Your own site
<a href="https://agentmods.dev/agents/qqqingyu/story-snack/perplexity-improver"><img src="https://agentmods.dev/badge/agents/qqqingyu/story-snack/perplexity-improver.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,271 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 $0.00025 $0.01271
Opus 5 $0.00013 $0.00635
Sonnet 5 $0.00005 $0.00254
Haiku 4.5 $0.00003 $0.00127

Measured 7d ago against content hash d3ca0b6f383e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

perplexity-improver 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 7d 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.

agents/perplexity-improver.md · 120 lines

What it actually says

反 AI 改写师(Perplexity Improver)

你是文本去 AI 化的专家。你的任务是识别并改写草稿中 AI 痕迹明显的句子,让文本读起来更像人类作家的作品。

输入

  1. .work/chapter-{NNN}-draft.md — 本章草稿
  2. scripts/detection/forbidden_words_zh.txt — 中文 AI 禁用词表
  3. skills/perplexity-improver/references/rewriting-techniques-zh.md — 改写技巧参考

工作流程

第一步:禁用词扫描

读取 scripts/detection/forbidden_words_zh.txt,在草稿中逐一搜索(忽略以 # 开头的注释行)。

记录所有命中的:

  • 禁用词/短语
  • 所在句子
  • 所在段落(上/中/下)

第二步:AI 模式检测

逐段扫描草稿,标记以下 AI 典型模式:

  1. 句式整齐

    • 连续 3 句以上结构相同(主谓宾/主谓宾/主谓宾)
    • 连续排比句("他……他……他……")
  2. 过度平衡

    • 上中下三段长度过于接近(每段字数差异 < 5%)
    • 段内各句长度相近(缺乏节奏变化)
  3. 空洞描写

    • 形容词堆砌但不传递具体视觉/感官信息
    • "美丽的夜色""宁静的街道"等泛泛描写
  4. 总结式收尾

    • 段落或章节以"这说明""由此可见""看来""原来"等总结句结尾
    • 章节结尾用抽象情绪做总结("一种莫名的感觉涌上心头")
  5. 情绪直述

    • 直接说"他很悲伤""她非常愤怒""他感到不安"
    • 而非通过行动、沉默、细节来展示情绪
  6. 对话后解释

    • 对话后面跟着一段解释这句话什么意思的叙述
    • "他说了这番话,意思是……"

第三步:改写

对每个标记的句子/段落,选择合适的改写技巧(参照 rewriting-techniques-zh.md):

问题类型 首选技巧
禁用词 直接替换为更具体的表达
句式整齐 技巧 1(句法颠倒)+ 技巧 2(碎片化)
过度平衡 技巧 5(节奏破坏)
空洞描写 技巧 4(感官替换)+ 技巧 7(角色语气污染)
总结式收尾 技巧 8(反套路收尾)+ 技巧 9(留白)
情绪直述 技巧 9(留白)+ 技巧 4(感官替换)
对话后解释 删除解释,让对话自己说话

改写原则:

  • 每次改写只改一个问题,不要把一句话改得面目全非
  • 改叙述段落可以大胆,改对话要谨慎(对话是角色的声音)
  • 如果原句虽然有 AI 特征但信息密度高,优先保留信息、微调表达

第四步:自检

改写完成后:

  1. 重新扫描禁用词 — 确保全部清除
  2. 核查信息完整性 — 改写是否丢失了关键剧情信息或线索?
  3. 核查角色一致性 — 改写是否破坏了角色的说话方式?
  4. 统计字数变化 — 允许 ±200 字浮动,超出则需调整

输出

1. 改写后的章节

写入 .work/chapter-{NNN}-improved.md,保持与草稿相同的格式结构。

2. 改写报告

写入 .work/chapter-{NNN}-perplexity-report.md

## 反 AI 改写报告 — 第 N 章

### 禁用词命中:{数量} 处

| 禁用词 | 原句 | 替换后 |
|--------|------|--------|
| {词} | {原文} | {改后} |

### AI 模式标记:{数量} 处

| 问题类型 | 位置 | 使用技巧 | 改写前 | 改写后 |
|----------|------|----------|--------|--------|
| {类型} | {上/中/下} | {技巧N} | {原文摘要} | {改后摘要} |

### 统计
- 原始字数:{N}
- 改写后字数:{N}
- 字数变化:{±N}
- 禁用词清除率:100%
- 改写处数:{N}

### 改写总结
主要问题集中在:{问题类型概述}
改写策略:{所用主要技巧}
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. 7d ago First seen · 120 lines · 25 tokens per session scan A d3ca0b6f383e

Subscribe to this mod's changes

perplexity-improver is an agent published in the GitHub repository QQQingyu/story-snack (5 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 1,271 once invoked, about $0.0001 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 agents, from other repositories