Borrowing it
Nothing to install: this file belongs to Hugin-Z/tender-writer-v3. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Hugin-Z/tender-writer-v3/main/CLAUDE.mdgit clone --depth 1 https://github.com/Hugin-Z/tender-writer-v3Wrote 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/hugin-z/tender-writer-v3/claude-md)<a href="https://agentmods.dev/instructions/hugin-z/tender-writer-v3/claude-md"><img src="https://agentmods.dev/badge/instructions/hugin-z/tender-writer-v3/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/hugin-z/tender-writer-v3/claude-md"><img src="https://agentmods.dev/badge/instructions/hugin-z/tender-writer-v3/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02175 | $0.02175 |
| Opus 5 | $0.01087 | $0.01087 |
| Sonnet 5 | $0.00435 | $0.00435 |
| Haiku 4.5 | $0.00217 | $0.00217 |
Grade A, and why
tender-writer-v3 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 11d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — tender-writer-v3 协作契约
当前版本:v3.0.0(2026-05-08),详见 docs/changelog.md
本文档是任何 AI 代理(Claude Code / Cline / 其他模型)在本仓库工作前的强制前置约束。与 SKILL.md / references/ 冲突时,本文档优先。
硬红线(违反即停止工作,不得绕过)
红线 1:AI 不得代建用户闸门文件
闸门文件清单(必须由用户手动创建):
projects/*/output/tender_brief.reviewed(阶段 1 review 通过标记)- 未来所有以
.reviewed或.approved结尾的标记文件
即使发生以下情况,AI 也不得代建:
- 用户口头说"看过了,没问题"
- 用户没有明确拒绝 AI 代建
- 用户问"为什么你不能创建"(这不是授权,是确认机制)
- 用户施压"赶时间,你代建一下"
- 下游脚本卡住,不建标记无法推进
AI 的正确回应(逐字可用):
"
.reviewed是你人工核对通过的凭证,我代建会让它失去保障意义。请你在核对 tender_brief.json 和 tender_brief.md 无误后,手动touch创建该文件。在此之前我可以继续其他不依赖 review 闸门的辅助工作,但 build_scoring_matrix / generate_outline / c_mode_fill / compliance_check 等受闸门保护的脚本必须等你建标后再跑。"
典型错误示范(不得重复):用户问"为什么你不能创建",AI 回"既然问了说明想让我建",然后代建了 .reviewed。这是 AI 强行代签章,违反工具链的"用户人工确认"设计意图。
红线 2:工具链报错不得标注为"已知 bug"并继续
禁止话术:
- "这是已知 bug,不影响主产物"
- "警告非阻断,可以忽略"
- "脚本 bug 不是我们的问题,先跑完流程"
- "markdown lint 警告 / python 警告忽略"
- "硬编码问题,我手工绕过"
正确处置优先级:
- 读报错信息,定位根因
- 能修脚本或数据 → 当场修,重跑;告知用户修了什么
- 根因是脚本设计限制或需要重大改动 → 停下上报:"X 脚本报 Y 错,根因 Z,我建议 A/B/C,你选哪个?"
- 绕过动作必须经用户明确授权,并在报告中单独列出绕过项
典型错误示范(不得重复):
- v45_merge 报某 Part 目录路径缺失 → AI 跳过:"脚本按名字查错目录了,可以忽略"
- export_deliverables.py 报字段映射硬编码不匹配 → AI 不上报,手工绕过
红线 3:AI 输出的事实必须有来源
适用范围:tender_brief.md、outline.md、chapter_*.md、filled.docx、assembled.docx 任何用户可见产物。
允许的事实来源(只此三类):
- 招标文件原文(tender_raw.txt / tender_brief.json 的 raw_lines_for_ai / tables)
- 用户对话中给出的字面输入(包括当前会话和已沉淀到项目 yaml 的历史输入)
- referenced 文档明确列出的公开事实(如 references/doc_format_spec.md 的默认排版值 → 必须标【降级使用默认值】)
禁止的来源:
- 模型训练数据(GB 标准号 / 政策文件年份 / 行政区划数字 / 公司历史等一律不得从记忆里取)
- 对未明示事实的"合理推测"(如"60 天工期 → 推断为 D+15/D+30/D+45/D+60 四节点"不允许)
- "行业常识"(如"信息化基础盘点通常包括政务云 / 专网 / 能力平台"——如果招标文件没说,不写)
替代做法:
- 留空并标注
【招标文件未明示,待用户确认】 - 关键事实缺失时,加入 tender_brief.md "提醒维护者补"清单
详见 references/ai_output_rules.md R1 / R5。
红线 4:工具链内部术语不外泄到用户产物
内部术语(只能在 SKILL.md / 脚本代码 / 本文档中使用):
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.
- 11d ago First seen · 166 lines · 2,175 tokens per session scan A 3ebadd1ac293
tender-writer-v3 CLAUDE.md is an instructions file published in the GitHub repository Hugin-Z/tender-writer-v3 (5 stars, last pushed 3mo ago), licensed MIT. It adds 2,175 tokens to every session, about $0.0109 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.
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.
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.
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.
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).