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 commands/snakeying/textum/scaffold-checkgit clone --depth 1 https://github.com/snakeying/TextumWrote 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/commands/snakeying/textum/scaffold-check)<a href="https://agentmods.dev/commands/snakeying/textum/scaffold-check"><img src="https://agentmods.dev/badge/commands/snakeying/textum/scaffold-check.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 | $0.00000 | $0.01314 |
| Opus 5 | $0.00000 | $0.00657 |
| Sonnet 5 | $0.00000 | $0.00263 |
| Haiku 4.5 | $0.00000 | $0.00131 |
Grade A, and why
scaffold-check 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
阶段2b: GLOBAL-CONTEXT 校验
读取:docs/GLOBAL-CONTEXT.md | 写入:无(只输出 FAIL/PASS;不修改文件) | 模板:N/A
输出 FAIL/PASS 清单;不修改任何文件。
输出规则(只读)
- 不输出 GC 原文
- 若存在任何
FAIL:- 输出
FAIL清单(F-001起编号;每条必须包含以下字段):定位:GC 章节路径(如## 4. 业务规则(必填))+(尽量)稳定ID(BR-###等)或表格行语义定位;避免行号问题:1 句期望:可机械执行的“替换目标/格式”(能推导就写出来)影响:H/M/L修复:只给 1 个动作(通常是“把本 FAIL 清单粘贴给 /scaffold 并按定位逐条修正” + 本条的最小修改点)
- 末尾追加:
修正:将 FAIL 清单作为可选输入粘贴给 /scaffold,逐条修正 docs/GLOBAL-CONTEXT.md重跑:/scaffold-check
- 然后结束
- 输出
- 否则(无
FAIL):输出PASS,并在末尾追加:下一步:/split-plan
FAIL 校验项(机械性门禁)
0) 文件存在
docs/GLOBAL-CONTEXT.md必须存在
1) 结构完整性(不得缺章)
必须包含以下一级章节(缺失即 FAIL):
## 1. 技术栈(必填)## 2. 项目结构(必填)## 3. 枚举值定义(必填;无则写 N/A)## 4. 业务规则(必填)## 5. 权限矩阵(必填)## 6. 数据模型概览(必填;如无 DB 写 N/A)## 7. 命名规范(如适用;否则写 N/A)## 8. API规范(必填)
2) 占位符与代码块(不得残留)
- GC 中不得出现 fenced code blocks(```);出现即
FAIL - GC 中不得残留任何模板占位符;命中任一即
FAIL:TBD[...]BR-###(仍为占位)A/D/O4XX/5XX
- 方括号使用规则(避免误伤路由/路径):在全文中若出现
[或]:- 允许:Markdown 链接
[text](...) - 允许:路径/路由 token 中的 Next.js 风格动态段(
[必须紧跟在/或\\之后,且[]内不得包含空白、/、\\),如/posts/[slug]、app/[id]/page.tsx - 其余一律视为模板占位符残留 →
FAIL
- 允许:Markdown 链接
3) 规则表最小可用性
- 在第 4 节业务规则表(表头包含
| ID |)中:- 必须存在规则表(表头包含
| ID |),且至少 1 行数据 - ID 列必须包含至少 1 条
BR-001形式的 ID - ID 列中的
BR-001形式 ID 必须唯一 - 不得出现占位符
BR-###
- 必须存在规则表(表头包含
4) 权限矩阵最小可用性
- 第 5 节必须包含权限矩阵表格,且至少 1 行数据
- 表格中每行
权限必须严格为A/D/O之一 - 不得出现
A/D/O
5) 噪音控制(不得把 PRD 片段塞进 GC)
docs/GLOBAL-CONTEXT.md中不得出现任何 PRD 锚点引用(出现即FAIL),包括任何PRD#...或<!-- PRD#... -->- 允许出现
docs/PRD.md作为“来源文件名/描述”;但禁止引用 PRD 的具体位置/片段(如 PRD 章节号定位、或复制 PRD 原文大段)
6) 项目验证命令表(必须存在;可为 N/A)
- 在第 2 节
## 2. 项目结构(必填)中必须包含小节:### 项目验证命令(如适用;否则写 N/A) - 该小节下必须存在表格,且表头必须为:
| 类型 | 命令 | 说明 | - 表格必须至少包含 1 行数据(不含表头与分隔行)
- 每行必须包含 3 列:
类型/命令/说明(按|分隔) 类型必须为以下之一:gate:<name>(失败阻断)opt:<name>(失败仅记录非阻断项)N/A
- 若某行
命令 = N/A:该行类型与说明也必须为N/A - 若某行
命令 != N/A:该行类型必须以gate:或opt:开头;不得为N/A
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 · 87 lines · 0 tokens per session scan A d7cda8ede048
scaffold-check is a command published in the GitHub repository snakeying/Textum (41 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,314 tokens. 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 commands, from other repositories
ask
数学研究操作系统入口:自动诊断用户意图,路由到思想透镜、数学知识库或设计翻译层。 English: Math Research OS entry: auto-diagnose user intent, route to thinking lenses, math knowledge base, or design translation layer.
ask
Math Research OS entry: auto-diagnose user intent, route to thinking lenses, math knowledge base, or design translation layer.
planwt
You are the orchestrator for a bounded worktree task.
statuswt
You are checking the status of all active worktree task files in the project.
finishwt
You are finishing a worktree task.
git
Git operations with intelligent commit messages and workflow optimization.