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-plangit 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 | $0.01295 |
| Opus 5 | $0.00000 | $0.00647 |
| Sonnet 5 | $0.00000 | $0.00259 |
| Haiku 4.5 | $0.00000 | $0.00129 |
Grade A, and why
split-plan 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
阶段3a: Story 拆分规划(/split-plan)
读取:docs/PRD.md(只读) | 写入:docs/split-plan.yaml(纯 YAML;不包含 ```) | 模板:.claude/textum/split-plan-template.yaml | 可选输入:SPLIT_REPLAN_PACK
生成 split-plan 规划 pack;不生成 Story 文件。
最小读取范围(必须;避免通读)
- PRD:
5.1 功能清单、9.2 接口清单(必填)
硬约束(必须遵守)
N/A_STRICT 判定口径(权威;逐字一致;禁止改写):
-
定位 PRD 小节
### 9.2 接口清单(必填)的正文(标题行之后到下一同级小节标题之前) -
判定
N/A_STRICT = true当且仅当:正文去掉空行并 Trim 后仅剩 1 行且该行严格等于N/A -
只做规划:不生成任何 Story 文件(不写入
docs/story-*-*.md) -
输出必须严格按
.claude/textum/split-plan-template.yaml的 YAML 结构(字段齐全;不得额外加 Markdown 文本;不得额外加键) -
docs/split-plan.yaml中不得出现TBD -
编号必须为
Story 1..N连续:stories[].n连续,且stories[].story == "Story {n}"stories[].slug必须唯一且符合kebab-case
-
stories[].modules必须为M-xx数组;不得写模块名 -
stories[].prereq_stories必须为["Story 1", ...]数组(无依赖则空数组);且必须可执行(仅允许依赖更小编号) -
stories[].goal必须非空(不得为TBD)
模块有效性与 P0 覆盖(本阶段必须做)
从 PRD 5.1 功能清单 抽取:
P0_modules =所有priority == P0的M-xx集合All_modules =PRD 中出现的全部M-xx集合
校验(任一不满足即必须在本命令内修正后再写文件):
- 对每个 Story 的
modules[]:每个M-xx必须属于All_modules - 对
All_modules中每个M-xx:必须至少出现在 1 个 Story 的modules[] - 对
P0_modules中每个M-xx:必须至少出现在 1 个 Story 的modules[]
API 分配(如适用)
先按 N/A_STRICT 判断 PRD 是否无 API:
- 若
N/A_STRICT = true:PRD_HAS_API = false - 否则:
PRD_HAS_API = true,并从 PRD9.2抽取P_api = {API-###}集合
若 PRD_HAS_API = false:
api_assignments必须为空数组
若 PRD_HAS_API = true:
- 覆盖 + 唯一归属:
- 对
P_api中每个API-###:必须在api_assignments[].api中出现且仅出现 1 次 api_assignments[].story必须引用stories[].story中存在的 Story
- 对
阈值预检(仅确定信号;减少重规划)
仅对“每个 Story 分配了多少 API”做预检(按 api_assignments 计数;不预测 TBL/验收/功能点数量):
api_assigned(Story N) =api_assignments中story == "Story N"的行数- 目标:尽量让每个
api_assigned ≤ 3 - 若出现
api_assigned = 4–5:允许写入,但输出DECISION清单(见“输出规则”) - 若出现
api_assigned ≥ 6:不得写入;必须先拆分/重分配(增加 Story 或调整边界)直到消除
重规划模式(当提供 SPLIT_REPLAN_PACK)
目标:把 pack 标记的过大 Story 拆成更小的 Story,并更新 docs/split-plan.yaml 重新满足门禁。
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 14add513a9a4
split-plan 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 1,295 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
Math Research OS entry: auto-diagnose user intent, route to thinking lenses, math knowledge base, or design translation layer.
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.
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.
checklist
Generate a custom checklist for the current feature based on user requirements.