writing-team-workbench: Instructions file for Claude Code

CLAUDE.md

writing-team-workbench CLAUDE.md is an instructions file for Claude Code from lisitan/writing-team-workbench. It costs 1,468 tokens per session, scanned A, original, MIT.

Project instructions for a Chinese-language writing workspace that uses eight specialist writing commands. They define the workflow, source checking, review rules, confirmation steps, and project status tracking.

In plain words
What is it for?
They guide research, planning, drafting, editing, title approval, image planning, and final layout for article projects. They also describe how to update project files and handle images.
Why use it?
They give the writing agents a shared process and record of what has been completed. This helps prevent stages from being skipped or different agents from editing the same article at once.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions Claude Code; mentions Codex.

This is lisitan/writing-team-workbench's own configuration. It tells Claude Code how to work on writing-team-workbench itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything writing-team-workbench configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lisitan/writing-team-workbench. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lisitan/writing-team-workbench/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/lisitan/writing-team-workbench

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 writing-team-workbench CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lisitan/writing-team-workbench/claude-md.svg)](https://agentmods.dev/instructions/lisitan/writing-team-workbench/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lisitan/writing-team-workbench/claude-md"><img src="https://agentmods.dev/badge/instructions/lisitan/writing-team-workbench/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,468 This file is loaded in full into every session.
When invoked 1,468 The same file — it is already loaded in full.
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 $0.01468 $0.01468
Opus 5 $0.00734 $0.00734
Sonnet 5 $0.00294 $0.00294
Haiku 4.5 $0.00147 $0.00147

Measured 7d ago against content hash 4d582d20546c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

writing-team-workbench CLAUDE.md 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.

CLAUDE.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE

这个仓库使用 8 位中文写作专家命令来推进文章。

.claude/commands/.claude/skills/ 是 Codex 与 Claude Code 共用的真源,两端共用同一套专家规则,不单独维护另一套。

开始位置

先读:

  • README.md
  • 03-方法/8专家写作流水线.md
  • 03-方法/人机确认门规则.md
  • 03-方法/项目状态看板规则.md
  • 03-方法/标题确认规则.md
  • 03-方法/文章体裁适配规则.md
  • 03-方法/资料源与核查规则.md
  • 03-方法/品控原则.md
  • 03-方法/金线9条.md
  • 03-方法/AI写作痕迹检测规则.md
  • 03-方法/去AI味写作规则.md
  • 03-方法/写作天团品控门禁.md
  • 05-资产/选题池.md
  • 05-资产/素材库.md
  • 05-资产/个人风格画像.md
  • 当前文章项目的 README.md
  • 当前文章项目的 项目状态.md
  • 当前文章项目的 资料.md

每次进入或恢复某文章项目时,还要检查 Git 状态。项目状态.md 是跨 Agent 的持续检查点:在产生实质文件改动、验证结论、阶段变化、用户反馈或阻塞后立即更新,不必等到会话结束。

同一篇文章严格串行:若 项目状态.md 显示已有 Agent 正在执行或尚未完成状态更新,不得同时写入该文章项目。不同文章项目可以并行;只读研究不得直接写入当前项目。

默认执行方式

如果用户调用写作天团短命令:

  1. 判断当前要处理的是选题池、文章项目还是素材归档。
  2. 读取对应 .claude/skills/*/SKILL.md
  3. 读取项目资料和上一位专家产物。
  4. 严格按该命令的角色职责、资料源规则和能力边界输出。
  5. 如果是张素材或吴查查,必要时联网,并把来源写回 资料.md
  6. 把结果写入项目的 过程/产出/,并在阶段、确认门、核查风险、标题状态、配图状态或资产回流变化时更新 项目状态.md
  7. 严格遵守确认门:策划案、初稿、标题、配图方案未确认前,不推进后续关键阶段。
  8. 如果是陈排版,额外生成 产出/配图方案.md;仅在用户明确要求生成实图且配图确认已通过时,调用 tools/image-generation/image_generate.mjs
  9. 如果要把图片插入最终正文,先调用 tools/image-bed/upload_image.mjs 上传图床;正文使用图床 URL,本地图片路径只记录在 产出/配图方案.md
  10. 每次实质进展后更新 项目状态.md 的当前工作、已验证结果、未验证风险、需要用户决定的内容、下一位 Agent 的唯一动作和最近状态变化;不要重复记录可由 Git diff 查到的聊天过程。

如果用户调用 /选题入池,只更新 05-资产/选题池.md,不创建项目。

如果用户调用 /项目立项,只创建或补齐标准项目结构,不写正文。

如果用户调用 /素材归档,只更新 05-资产/素材库.md 和项目资产回流状态。

重要原则

  • 不要跳过中间产物。
  • 不要跳过确认门;AI 做创造,人做判断。
  • 用户反馈统一写入 过程/反馈记录.md
  • 不要把事实核查和润色混在一起。
  • 不要把排版稿写成解释文档。
  • 不要把配图方案、prompt 或图片生成记录混进最终正文。
  • 不确定的事实要显式标注为“待核查”。
  • 搜不到来源不等于错误,只能标为待核查或未找到可靠来源。
  • 吴查查必须输出断言核查表,并把核查摘要写回 项目状态.md
  • 陈排版必须输出标题候选评估表;标题未确认时不把推荐标题当成最终标题。
  • 柯短文负责长文转短文(朋友圈/X/即刻/小红书)与直接创作短文,遵守 03-方法/短文转化规则.md;小红书图文只给配图建议,不生成实图。
  • 任何文章都要经过“具体读者、真实任务、可感知素材、建模、立靶子、上架检查”的品控意识。
  • 任何文章都必须过“金线9条”的通用版:读者服务、对象感、挑战开篇、克服炫技、认知落差、注意力管理、消除理解障碍、便于带走、尊重看不见的人。
  • 当前默认体裁是观点文、复盘文、方法文;默认平台是公众号/长文,不要把所有文章写成教程稿或课程稿。
  • 写正文、审稿和排版时必须把 03-方法/AI写作痕迹检测规则.md03-方法/去AI味写作规则.md 作为内部改稿标准,避免 AI 助手式开头、机械分点、万能总结、空泛大词和过密洞察句,也不要为了伪装真人机械打乱文本。
  • 配图默认服务公众号/长文的封面、首图和文内图;小红书图文只给配图建议,不默认生成实图、封面、短视频封面或销售海报。
  • 策划案未确认时,不写初稿;标题未确认时,不写最终标题;配图方案未确认时,不生成实图、不插入图片。
  • 图床上传失败时,不把本地图片路径临时写进最终正文。
  • 个人笔记库只使用 personal-notes-readonly 做只读检索,不调用写入、更新、删除、标签、分享或上传工具。
  • 刘风格默认优先读取 05-资产/个人风格画像.md;只有需要重新校准风格或画像缺失时,才扫描 <你的风格样本目录>,且不得大段复制样本文字。

Read the full file on GitHub · 77 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. 7d ago First seen · 77 lines · 1,468 tokens per session scan A 4d582d20546c

Subscribe to this mod's changes

writing-team-workbench CLAUDE.md is an instructions file published in the GitHub repository lisitan/writing-team-workbench (20 stars, last pushed 21d ago), licensed MIT. It adds 1,468 tokens to every session, about $0.0073 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens