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 instructions/lisitan/writing-team-workbench/agents-mdgit clone --depth 1 https://github.com/lisitan/writing-team-workbenchWrote 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/instructions/lisitan/writing-team-workbench/agents-md)<a href="https://agentmods.dev/instructions/lisitan/writing-team-workbench/agents-md"><img src="https://agentmods.dev/badge/instructions/lisitan/writing-team-workbench/agents-md.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 | $0.01831 | $0.01831 |
| Opus 5 | $0.00915 | $0.00915 |
| Sonnet 5 | $0.00366 | $0.00366 |
| Haiku 4.5 | $0.00183 | $0.00183 |
Grade A, and why
writing-team-workbench AGENTS.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 4d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
这个仓库是一套写作天团工作台,服务于 Codex、Claude Code 与 Obsidian。
工作边界
- 优先生成 Markdown 文件。
- 外部能力只走本仓已配置的边界:个人笔记库只读检索;配图默认先生成方案,只有用户明确要求时才调用本地生图脚本生成实图。
- 不默认创建网页 UI。
- 不改动其他 vault,尤其不自动改动 Factory 知识库。
核心入口
- [[README]]
- [[03-方法/8专家写作流水线]]
- [[03-方法/人机确认门规则]]
- [[03-方法/项目状态看板规则]]
- [[03-方法/标题确认规则]]
- [[03-方法/文章体裁适配规则]]
- [[03-方法/品控原则]]
- [[03-方法/金线9条]]
- [[03-方法/AI写作痕迹检测规则]]
- [[03-方法/去AI味写作规则]]
- [[03-方法/写作天团品控门禁]]
- [[03-方法/十大选题模板]]
- [[03-方法/短文转化规则]]
- [[05-资产/选题池]]
- [[05-资产/素材库]]
- [[05-资产/短文素材库]]
- [[05-资产/个人风格画像]]
- [[04-示例/示例主题]]
- [[02-项目/示例-个人知识库不是收藏夹/README]]
目录结构
00-输入/:原始想法、写作需求、粘贴材料。01-角色/:9 位专家角色说明(8 长文专家 + 柯短文)。02-项目/:文章项目。03-方法/:流程、标准、复盘方式。04-示例/:示例素材。05-资产/:选题池和跨项目素材库。.claude/commands/:可调用命令。.claude/skills/:9 位专家的能力层。
项目规则
每篇文章使用一个项目文件夹:
02-项目/文章项目名/
├── README.md
├── 项目状态.md
├── 资料.md
├── 过程/
│ ├── 00-策划案.md
│ └── 反馈记录.md
└── 产出/
├── 文章草稿.md
├── 配图方案.md
└── images/
└── prompts/
项目状态.md 同时是跨 Agent 的持续检查点,不是只给人看的看板。每次进入某文章项目,先读 README.md、项目状态.md、资料.md 和 Git 状态;不要覆盖来源不明的未提交修改。
发生以下任一情况后,立即更新 项目状态.md,不必等用户说要切换 Agent:阶段推进、确认门变化、核查结论、用户反馈、阻塞、实际文件改动或下一步改变。状态只保留当前真相和最近几条变化,不写聊天逐字稿。
同一篇文章严格串行:同一时刻只允许一个 Agent 写入项目文件。当前 Agent 必须在 项目状态.md 标明当前工作并完成状态更新后,下一位才能接手;不同文章项目可以并行,只读准备工作不得直接写入当前项目。
命令规则
命令必须使用中文文件名和中文命令名:
/选题入池/项目立项/赵选题/张素材/王整理/刘风格/李文章/吴查查/周审稿/陈排版/柯短文/素材归档
每个命令默认读取当前文章项目,并把产物写入固定位置。若用户没有指定项目,先请用户提供项目路径或文章主题。
命令只做入口,具体执行能力必须遵守对应 .claude/skills/*/SKILL.md。
/选题入池、/项目立项、/素材归档 是连续生产系统命令,不替代 8 位专家流水线。
资料源规则
- 当前项目是第一上下文。
- 本地资产层用于跨项目复用:
05-资产/选题池.md、05-资产/素材库.md。 - 个人笔记库用于查用户自己的历史想法、灵感、案例、旧文章和个人经验。
- 张素材和吴查查可按需联网。
- 张素材和吴查查必须把可复用素材、外部来源和核查记录写回当前项目
资料.md。 - 陈排版必须把配图策略、prompt、生成记录和图片风险写入当前项目
产出/配图方案.md。 - 默认采用硬停确认门:策划案、初稿、标题、配图方案未确认前,不推进后续关键阶段。
- 用户反馈统一写入当前项目
过程/反馈记录.md。 - 每个文章项目必须维护
项目状态.md,作为当前阶段、下一步、确认门、核查风险、标题状态、配图状态和资产回流状态的总控台。 项目状态.md还必须写明当前工作、文件边界或任务归属、已验证结果、未验证风险、需要用户决定的内容和下一位 Agent 的唯一动作;它是 Codex 与 Claude Code 的共同交接真源。- 吴查查必须输出断言核查表,并把断言总数、待核查、冲突、建议删除和最高风险写回
项目状态.md。 - 陈排版必须输出标题候选评估表;标题未确认前,不得把推荐标题写成最终标题。
- 个人笔记库只使用
personal-notes-readonlyMCP server,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>。 - 文章实图插入正文前必须先保留本地备份,再通过
tools/image-bed/upload_image.mjs上传图床;最终产出/文章草稿.md使用图床 URL,不使用本地图片路径。
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.
- 4d ago First seen · 127 lines · 1,831 tokens per session scan A 852e27430f41
writing-team-workbench AGENTS.md is an instructions file published in the GitHub repository lisitan/writing-team-workbench (20 stars, last pushed 19d ago), licensed MIT. It adds 1,831 tokens to every session, about $0.0092 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 instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.