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.
git 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/split-check2)<a href="https://agentmods.dev/commands/snakeying/textum/split-check2"><img src="https://agentmods.dev/badge/commands/snakeying/textum/split-check2/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/commands/snakeying/textum/split-check2"><img src="https://agentmods.dev/badge/commands/snakeying/textum/split-check2.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 | $0.00000 | $0.01883 |
| Opus 5.5 | $0.00000 | $0.00753 |
| Sonnet 5.5 | $0.00000 | $0.00377 |
| Haiku 4.5 | $0.00000 | $0.00188 |
Grade A, and why
split-check2 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 1mo 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
阶段4b: Story 拆分校验（引用可追溯 + API Smoke / split-check2）
读取：docs/split-check-index-pack.yaml、docs/GLOBAL-CONTEXT.md（只读）、docs/PRD.md（只读） | 写入：无（只输出 FAIL/PASS；不修改文件） | 模板：N/A
对齐 GC/PRD 做引用可追溯与（有 API 时）Smoke Test。
最小读取（必须；避免通读）
只允许引用本节列出的内容范围；其余一律视为不可用。
- 解析 index pack：得到 Story 列表、模块覆盖、引用集合、API 分配
- 读取 GC：仅第 4 节业务规则表（得到合法
BR-###集合） - 读取 PRD（只读以下索引章即可）：
5.1 功能清单（模块 + 优先级，得到P0模块集合与全部M-xx集合）6. 业务规则（规则表，得到BR-###集合）8.0 功能点→落点映射（得到FP-001集合）8.1 表清单（得到TBL-###集合）9.2 接口清单（按N/A_STRICT判断是否无 API；得到API-###集合）
- 仅当触发 API Smoke Test 时：再读取 PRD
9.3 接口详情（按锚点<!-- PRD#API-### -->定向检索）
输出（只读）
- 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：目标文件（docs/split-check-index-pack.yaml/docs/GLOBAL-CONTEXT.md/docs/PRD.md）+ 章节路径或稳定ID（BR-###/FP-###/TBL-###/API-###或<!-- PRD#... -->）；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（必要时先重跑/split-check1以重写docs/split-check-index-pack.yaml）
- 末尾追加：
修正：按 FAIL 清单逐条修复（必要时重跑 /split-check1 重新写入 docs/split-check-index-pack.yaml）重跑：/split-check2
- 然后结束
- 输出
- 否则：输出
PASS，并提示下一步：/split-checkout
FAIL 校验项（机械性门禁）
0) 基础门禁
docs/split-check-index-pack.yaml必须存在且可解析- 根键必须为
SPLIT_CHECK_INDEX_PACK: v1 docs/GLOBAL-CONTEXT.md必须存在docs/PRD.md必须存在
0.5) index pack 占位符门禁
docs/split-check-index-pack.yaml中不得出现任何模板占位符；命中任一即FAIL：TBDStory NM-xxFP-###/BR-###/TBL-###/API-###
1) GC 规则引用一致性（GC#BR）
- 对 index pack
summary.refs.gc_br_ids中每个BR-###：- 必须存在于 GC 第 4 节规则表的 ID 列；否则
FAIL
- 必须存在于 GC 第 4 节规则表的 ID 列；否则
2) PRD 规则引用一致性（PRD#BR）
- 对 index pack
summary.refs.prd_br_ids中每个BR-###：- 必须存在于 PRD 第 6 节规则表；否则
FAIL
- 必须存在于 PRD 第 6 节规则表；否则
3) PRD 表引用一致性（PRD#TBL）
- 对 index pack
summary.refs.prd_tbl_ids中每个TBL-###：- 必须存在于 PRD
8.1 表清单；否则FAIL
- 必须存在于 PRD
3.5) 功能点引用与覆盖（FP）
令：
P_fp =PRD8.0 功能点→落点映射表中出现的FP-001集合S_fp =index packsummary.refs.fp_ids集合
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.
- 1mo ago First seen · 122 lines · 0 tokens per session scan A ed4a9527d0ac
split-check2 is a command published in the GitHub repository snakeying/Textum (41 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,883 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
statuswt
You are checking the status of all active worktree task files in the project.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.