A command for splitting a product requirements document into implementation stories. A product requirements document describes what a product must do, while a story is a smaller, traceable piece of that work.

Use it to create story files from a split plan, attach feature, business-rule, table, and API references, and write acceptance checks without changing the approved plan.

It preserves the planned story boundaries, links each story to the relevant requirements and interfaces, and checks that the generated files have the required structure.

split — Command by snakeying

Install

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.

agentmods

npx agentmods add commands/snakeying/textum/split

Clone the repo

git clone --depth 1 https://github.com/snakeying/Textum

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,011 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.02011
Opus 5	$0.00000	$0.01006
Sonnet 5	$0.00000	$0.00402
Haiku 4.5	$0.00000	$0.00201

Measured 2d ago against content hash 4e9fe1064ff6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

split 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.

outdated/.claude_outdated/commands/split.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

阶段3: Story 拆分（/split）

读取：docs/split-plan.yaml、docs/PRD.md（只读）、docs/GLOBAL-CONTEXT.md（只读） | 写入：docs/story-*-*.md | 模板：.claude/textum/story-template.md

按 split-plan 生成 Story 文件（含 YAML front-matter）。

最小读取范围（必须；避免通读）

split-plan：全量（用于 Story 边界 / 模块 / 依赖 / API 分配）
GC：仅第 4 节业务规则表（用于挑选可用 BR-### 写入 refs.gc_br）
PRD：
- 5.2 功能规格：按模块抽取 FP-001 与功能点描述（用于 Story 的 FP 分配与“功能点”章节）
- 6. 业务规则：仅当需要写入 refs.prd_br 时，按需抽取可引用的 BR-###
- 8.0 功能点→落点映射：用于把 FP-001 映射到本 Story 必须声明的 refs.prd_tbl[] / artifacts.*[]
- 8.1 表清单：用于校验/选择可用 TBL-###（如适用）
- 9.2 接口清单：仅用于确认接口 ID 集合（Story 的 refs.prd_api 来自 split-plan 分配）

硬约束

不得更改 docs/split-plan.yaml 的 Story 编号/边界/API 分配：若发现不合理则停止并输出阻断原因（不写 Story 文件；需要先修正 split-plan）
每个 Story 文件必须包含 YAML front-matter（文件首部 --- ... ---），且字段齐全、可解析（结构以模板为准）
每个 Story 文件不得出现 fenced code blocks（```）
YAML front-matter 中所有 ID 必须为具体数字：
- modules[]: M-01
- fp_ids[]: FP-001
- refs.gc_br[] / refs.prd_br[]: BR-001
- refs.prd_tbl[]: TBL-001
- refs.prd_api[]: API-001
Story 模板章节不得缺失；无内容写 N/A；不得残留占位符（如 TBD、[功能描述]、M-xx、FP-###、Story N）
验收标准不得留空：
- ## 验收标准（必填） 章节下必须存在 - [ ] 条目，且每条必须包含非空描述（不得整行仅为 - [ ] 技术验收: / - [ ] 用户验收:，也不得为 N/A）
若 docs/split-plan.yaml 的 api_assignments 为空（无 API）：
- 每个 Story front-matter refs.prd_api 必须为空数组
- 每个 Story 的 ## 接口 章节正文必须严格为 1 行 N/A

FP 分配规则（必须；机械可执行）

定义 P_fp：从 PRD ### 8.0 功能点→落点映射（必填） 表第一列抽取全部 FP-001，升序排序
定义 P_fp_by_module[M-xx]：从 PRD 5.2 各模块小节的「功能点」表抽取 FP-001（保留在 P_fp 中的），按 FP 升序排序
若任一 FP-001 在 PRD 5.2 的多个模块小节出现：停止并提示修正 PRD（保证 FP 唯一归属一个模块）
对每个模块 M-xx：
- 定义 S(M-xx)：split-plan 中 stories[] 里 modules 包含该 M-xx 的 Story 列表（按 n 升序）
- 若 S(M-xx) 为空：停止并提示修正 split-plan（必须覆盖该模块）
- 将 P_fp_by_module[M-xx] 依序按 round-robin 分配给 S(M-xx)：第 i 个 FP → S(M-xx)[(i-1) mod |S(M-xx)|]
对每个 Story：fp_ids = 分配给该 Story 的 FP 并集（升序）；不得为空
全局一致性：所有 Story 的 fp_ids 并集必须与 P_fp 完全一致（无遗漏/无重复归属）

Read the full file on GitHub · 93 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.

2d ago First seen · 93 lines · 0 tokens per session scan A 4e9fe1064ff6

Subscribe to this mod's changes

split 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 2,011 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.

Backend and APIs Documents Writing and docs claude-code claude-skill codex codex-skill skills vibe-coding

split

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

阶段3: Story 拆分（/split）

最小读取范围（必须；避免通读）

硬约束

FP 分配规则（必须；机械可执行）

What this file has done since we first saw it

Other commands, from other repositories

ask

ask

planwt

statuswt

finishwt

checklist