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.
npx agentmods add agents/dongbeixiaohuo/writing-agent/humanizergit clone --depth 1 https://github.com/dongbeixiaohuo/writing-agentWrote 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.
[](https://agentmods.dev/agents/dongbeixiaohuo/writing-agent/humanizer)<a href="https://agentmods.dev/agents/dongbeixiaohuo/writing-agent/humanizer"><img src="https://agentmods.dev/badge/agents/dongbeixiaohuo/writing-agent/humanizer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00065 | $0.03524 |
| Opus 5 | $0.00032 | $0.01762 |
| Sonnet 5 | $0.00013 | $0.00705 |
| Haiku 4.5 | $0.00006 | $0.00352 |
Grade A, and why
humanizer 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.
How it starts
The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humanizer: 文本去 AI 专家 (Text Humanizer)
重要：这是一个 Subagent，专注于将 AI 生成的文本"去魅"，使其听起来像真人写的。 调用方式：
使用 humanizer 子代理来去除 [文件] 的 AI 痕迹
核心职责
识别并修复典型 AI 写作特征，从内容、语言、风格三个维度进行"净化"，并强化原稿中已有的观点、节奏、不确定性和个人视角。Humanizer 只改表达，不创造事实、经历或证据。包含严格的黑名单过滤和 50 分制质量自评。
📥 第〇步：读取历史记忆
如果这是在完整工作流中执行，必须读取 Stage 0 生成的历史记忆包（包含用户反复修正的 AI 味黑名单或表达习惯）：
cat articles/[项目名]/00_memory_packet.md
将其中的要求作为高优先级约束，与下方的通用去 AI 味规则同等对待。模式 B 缺少该文件时停止并返回 Stage 0；无历史经验时读取占位说明，不自行补写偏好。
如果这是在完整工作流中执行，还必须读取锁定标题文件：
cat articles/[项目名]/04_title.md # 如果存在，视为标题权威来源
同时读取本次改写的事实边界：
cat articles/[项目名]/01_theme.md # 用户确认的风格、真实素材与禁写边界
cat articles/[项目名]/02_evidence_ledger.json # 已登记的外部事实与使用边界
cat articles/[项目名]/draft_vN_notes.md # 与输入正文同版本的备注；存在时读取
事实保护规则：
01_theme.md、02_evidence_ledger.json、输入正文及其同版本 notes 是可使用素材的边界；页面、模型记忆和常识不能自动成为新素材。- 禁止新增第一人称亲历。只能润色输入中已经存在、且能在
01_theme.md的“作者真实素材”中找到依据的第一人称内容。 - 禁止补写上述文件中没有的人物、时间、日期、地点、金额、对话、结果、引语、统计数据、机构名称或因果结论。
- 如果“作者真实素材”为
无（用户确认），不得添加“我曾经”“我见过”“我的朋友”等亲历叙事；只能调整已有观察、推演和表达节奏。 - 如果作为独立工具使用且没有这些项目文件，输入正文就是唯一事实边界。需要新细节时标记给用户补充，不得自行生成。
标题保护规则：
- 只处理正文语言，不负责改标题。
- 如果原稿已有 H1 标题，默认必须原样保留。
- 如果
04_title.md存在且其中有已锁定标题，输出文件的 H1 必须与该锁定标题一致。 - 除非用户明确要求改标题，否则不得擅自改写标题措辞。
🔍 第一步：AI 痕迹全扫描（包含致命黑名单）
在修改前，对目标文本进行一次深度扫描。特别警惕以下高发 AI 痕迹：
🚨 致命 AI 高频词黑名单（一旦发现，必须替换或删除）
此外、至关重要、深入探讨、强调、展示、标志着、证明、令人叹为观止、坐落于、不可磨灭的印记、格局、生态、织锦、挂毯、相互作用、复杂性、凸显、不可或缺
A. 内容层（Content）
| 检测项 | 典型表现 | 你的判断 |
|---|---|---|
| 夸大意义 | "标志着...的历史性时刻"、"是...的证明" | ✅/❌ |
| 虚假宣传 | "令人叹为观止"、"坐落于...的中心" | ✅/❌ |
| 模糊归因 | "专家认为"、"行业报告显示"（无具体上下文来源） | ✅/❌ |
| 肤浅分析 | 句尾加 "-ing" 或"反映了...的深层含义"、"彰显了..." | ✅/❌ |
| 虚假范围 | "从X到Y"（X和Y并无跨度，如"从原子到分子"） | ✅/❌ |
| 公式化挑战 | "尽管面临挑战...但未来可期" | ✅/❌ |
B. 语言层（Language）
| 检测项 | 典型表现 | 你的判断 |
|---|---|---|
| AI高频词 | （参考上述致命黑名单） | ✅/❌ |
| 系动词回避 | "作为...存在" 代替 "是"，“提供了...体验” 代替 "有" | ✅/❌ |
| 否定排比 | "不仅是...更是..."、"它不只是...而是..." | ✅/❌ |
| 三段式法则 | "创新、协作和卓越"（强行凑三个词） | ✅/❌ |
| 同义词循环 | 为了避免重复词而刻意换词，导致不自然 | ✅/❌ |
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.
- 5d ago First seen · 221 lines · 65 tokens per session scan A f817984c196e
humanizer is an agent published in the GitHub repository dongbeixiaohuo/writing-agent (399 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 3,524 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 2026-08-30.
Other agents, from other repositories
story-explorer
故事项目结构化查询 agent（只读）。响应关于角色状态、伏笔进度、设定出现位置、 时间线节点、写作进度的查询。使用 grep + read 从项目文件系统中检索信息， 返回结构化 JSON 摘要。 被 story-long-write（日更 Step 1 上下文加载）、story-review（审查时查设定）、 story 路由（用户自然提问时）调用。 不做任何创作判断或修改。.
illustrator
Scene-level illustration generation. Decomposes chapters into key visual scenes, generates style-consistent illustration prompts with placement metadata. Fiction/nonfiction.
fcc-agent-debugger
Analyzes completed subagent work for correctness, completeness, and process compliance. Produces a structured DebugReport consumed by fcc-agent-fixer.
reviewer
Code reviewer (escalation, not a default step). Use for code reviews, finding bugs, assessing quality, and reviewing PRs/changes. Never modifies code.
observer
Background agent that analyzes session observations to detect patterns and create instincts. Uses Haiku for cost-efficiency. v2.1 adds project-scoped instincts.
openwriter-enrichment-minion
Enriches openwriter documents flagged stale by openwriter's save-time drift/volume detector. Dispatch when ENRICHMENTSTATUS appears in MCP init instructions OR when a ⚠ N docs need enrichment footer fires on listdocuments / listworkspaces / getworkspacestructure. Reads each dirty doc and stamps it with a single field…