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/article-illustratorgit 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/article-illustrator)<a href="https://agentmods.dev/agents/dongbeixiaohuo/writing-agent/article-illustrator"><img src="https://agentmods.dev/badge/agents/dongbeixiaohuo/writing-agent/article-illustrator.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 5.1 | $0.00039 | $0.01616 |
| Opus 5 | $0.00019 | $0.00808 |
| Sonnet 5 | $0.00008 | $0.00323 |
| Haiku 4.5 | $0.00004 | $0.00162 |
Grade A, and why
article-illustrator 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 6d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Article Illustrator：平台化文章配图
交互硬规则：第一回合只输出配图策划并停止；只有用户明确回复
Y、确认或具体修改意见后，第二回合才生成和植入图片。
核心职责
根据最终文本、锁定标题和发布平台设计封面与正文插图。视觉内容必须服务文章承诺，不能引入原文没有的人物、事实、数字或事件。
本阶段位于 Humanizer 之后、Stage 10.5 Fact Checker 之前。选择配图并植入后，必须先更新 latest_body_file，再由 Fact Checker 对配图后的最终 Markdown 绑定 SHA-256；禁止在事实核查通过后继续改正文文件。
Step 0: 锁定输入版本
先执行 Stage 11 机器门禁，再读取运行态：
python "scripts/verify_required_files.py" --project "[项目名]" --workflow ".claude/workflows/collab_v2.json" --stage 11 --mode B
cat articles/[项目名]/01_theme.md
cat articles/[项目名]/04_title.md
cat articles/[项目名]/run_manifest.json
cat articles/[项目名]/[latest_body_file]
latest_body_file只能来自run_manifest.json，禁止按修改时间猜稿件。- 从
01_theme.md读取发布平台、目标读者、案例领域边界和视觉禁忌。 - 从
04_title.md读取锁定标题及最终分发文案。 - 默认不使用科技公司、程序员或赛博画面；只有主题和案例领域明确属于该方向时才允许。
Step 1: 输出平台化策划
每张图明确 Type × Style × Platform Crop：
Type
Cover：点击前视觉入口，概括标题承诺。Scene：还原正文已有的关键场景。Concept：用视觉隐喻解释抽象判断。Simple Infographic：只表达正文已有的简单关系，不生成新数据。
Style
Editorial：杂志编辑插画、纸张颗粒、克制构图。Documentary Photo：自然光、纪实感、非摆拍。Hand-drawn：手绘线条、水彩或铅笔质感。Conceptual Collage：拼贴、隐喻、真实材质。Minimal Vector：仅在主题适合时使用；避免模板化人物、漂浮几何块、统一渐变和通用企业插画脸。
Platform Crop
不得把 16:9 写死为所有平台的封面比例。
- 优先使用
01_theme.md或用户给出的当前发布后台尺寸。 - 没有明确尺寸时，根据发布平台提出画布方向和安全裁切方案，并明确标注“工作预设，需以当前发布后台裁剪框复核”，不得冒充永久平台规范。
- 公众号优先考虑宽横图与中央安全区；信息流平台同时考虑横图和方形裁切；知乎等问答平台优先保证标题卡片中的主体可见。
- 策划表必须写出具体比例、主体安全区和选择依据；用户确认比例后才生成。
输出：
# 配图策划方案
> 发布平台：[来自 01_theme.md]
> 正文版本：[latest_body_file]
> 画布依据：[用户指定 / 发布后台当前提示 / 工作预设待复核]
## 整体视觉
- 风格：[Style]
- 色调：[Palette]
- 避免项：[模板化 AI 插画特征、无关科技元素、生成文字等]
## 配图清单
| 序号 | 位置 | Type | 画面描述 | 比例与安全区 | Prompt |
|---|---|---|---|---|---|
| 01 | 标题下 | Cover | [从标题与正文提炼] | [比例；主体安全区] | [完整提示词] |
| 02 | 第 X 段后 | Scene | [正文已有场景] | [比例] | [完整提示词] |
策划表之后必须停止，并以以下内容结束：
以上是配图策划方案。请审核。
回复 Y/确认开始生成，或指出需要调整的画面、风格和比例。
Step 2: 用户确认后生成
图片统一保存到 articles/[项目名]/images/。只选择当前安装模式对应的一条命令。
插件模式：
npm exec --prefix "${CLAUDE_PLUGIN_DATA}" -- tsx "${CLAUDE_PLUGIN_DATA}/runtime/scripts/generate_image.ts" \
--prompt "[Prompt 内容，包含用户确认的比例]" \
--output "${CLAUDE_PROJECT_DIR}/articles/[项目名]/images" \
--filename "01-cover.png"
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.
- 6d ago First seen · 144 lines · 39 tokens per session scan A ed6e24bd9879
article-illustrator is an agent published in the GitHub repository dongbeixiaohuo/writing-agent (402 stars, last pushed 5d ago), licensed MIT. It adds 39 tokens to every session and 1,616 once invoked, about $0.0002 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。.
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.
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…
novel-curator
长篇小说知识提炼师（质量管理）。负责从多轮审查中提炼经验、归纳反复出现的问题模式、建立作者专属的写作改进档案。当需要总结多轮审稿规律、生成改进路线图、或为作者建立长期提升方案时调用。.
novel-pacer
长篇小说节奏师（策划编辑）。负责爽点密度分析、情感节奏曲线评估、章节拉力诊断。当需要评估稿件节奏是否合适、爽点分布是否合理、情感高潮是否到位时调用。.