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/split-checkoutgit clone --depth 1 https://github.com/snakeying/TextumWhat 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 | $0.01006 |
| Opus 5 | $0.00000 | $0.00503 |
| Sonnet 5 | $0.00000 | $0.00201 |
| Haiku 4.5 | $0.00000 | $0.00101 |
Grade A, and why
split-checkout 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 2d 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.
What it actually says
阶段5: Split checkout(导出 Story 依赖图 / split-checkout)
读取:docs/story-*-*.md | 写入:docs/story-mermaid.md | 模板:N/A
仅导出依赖图;不修改任何 Story 文件。
最小读取(必须;避免通读)
- 读取所有 Story:只解析 YAML front-matter(首部
--- ... ---)
输出规则(只读)
- 不输出任何 Story 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:目标 Story 文件(docs/story-N-<slug>.md)+ YAML front-matter key(如prereq_stories)或门禁项;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“按定位修正对应 Story 文件”)
- 末尾追加:
修正:按 FAIL 清单逐条修复 docs/story-*-*.md 后重跑 /split-checkout重跑:/split-checkout
- 然后结束(不写文件)
- 输出
- 否则:
- 覆盖写入
docs/story-mermaid.md - 输出:
PASS已写入:docs/story-mermaid.md下一步:/story-check N
- 覆盖写入
硬约束(必须遵守)
- Mermaid 图必须仅由 Story 编号与
prereq_stories推导(不得脑补额外依赖)
执行步骤(必须按序)
1) 解析所有 Story(只看 YAML front-matter)
对每个 docs/story-*-*.md:
- 必须存在 YAML front-matter(文件首部
--- ... ---),且必须可解析为 YAML;否则FAIL - 根键必须包含
STORY: v1;否则FAIL - 抽取(仅用于构图):
story(严格形如Story 1)n(整数)prereq_stories[](形如["Story 1"];无依赖则空数组)
构造:
AllStories =按n升序的Story N列表Edges =对每个Story N与其每条prereq_stories,生成有向边:prereq -> Story N
2) 门禁(任一命中即停止;不写文件)
- 至少存在 1 个
docs/story-*-*.md AllStories中n必须唯一- 每个 Story:
story必须严格等于"Story {n}"prereq_stories[]中每个Story X必须存在于AllStories且X < n
3) 写入 docs/story-mermaid.md(覆盖写;严格按序)
写入内容必须严格为:
- 第一行:
# Story 依赖图 - 第二行:空行
- 第三行开始写入 1 个 Mermaid fenced code block(围栏为 3 个反引号字符
`):- 开始行必须为:三个反引号 +
mermaid - 第二行必须为:
flowchart TD - 节点(必须全量覆盖
AllStories;按n升序逐行输出):- 对每个
Story n:输出一行Story_{n}["Story {n}"]
- 对每个
- 边(必须全量覆盖
Edges;按prereq_n升序、再按story_n升序逐行输出):- 对每条边
Story a -> Story b:输出一行Story_{a} --> Story_{b}
- 对每条边
- 结束行必须为:三个反引号
- 开始行必须为:三个反引号 +
节点命名规则(必须):必须生成 Story_1["Story 1"] 形式的节点(避免空格导致 Mermaid 解析失败)。
开始
请确认 docs/story-*-*.md 已存在。
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.
- 2d ago First seen · 82 lines · 0 tokens per session scan A 0bb99d376a4f
split-checkout 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 1,006 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
pr-handle
Check out a PR, rebase onto main, triage open review comments, and validate skill changes.
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.
omg-legal
Command "omg-legal" from chenmitchell/omg-payment-skill, covering /omg-legal, 用法, ai 執行流程, 強制免責聲明 and 變數.
omg-pay
一句話觸發完整歐買尬金流整合。AI 接收此指令後,應依 guides/00-onboarding.md 定義之 onboarding 流程四問一次性呈現,並於使用者回覆「全部」或「預設」後進入 15 步自動整合。.