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/story-packgit 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/story-pack)<a href="https://agentmods.dev/commands/snakeying/textum/story-pack"><img src="https://agentmods.dev/badge/commands/snakeying/textum/story-pack.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 | $0.02742 |
| Opus 5 | $0.00000 | $0.01371 |
| Sonnet 5 | $0.00000 | $0.00548 |
| Haiku 4.5 | $0.00000 | $0.00274 |
Grade A, and why
story-pack 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 5d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
阶段6b: Story 执行包生成
$ARGUMENTS: Story 编号(如: 1)
读取:docs/story-$ARGUMENTS-*.md、docs/GLOBAL-CONTEXT.md(只读)、docs/PRD.md(只读) | 写入:docs/story-$ARGUMENTS-exec-pack.yaml(仅 PASS 时写入;纯 YAML;不包含 ```) | 模板:N/A
生成 1 个 STORY_EXEC_PACK,写入 docs/story-$ARGUMENTS-exec-pack.yaml,作为该 Story 的最小执行输入。
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。
- 读取 Story:仅解析 YAML front-matter 作为索引
- 读取 GC:按索引抽取片段(固定章节 + 规则表行 + 验证命令表)
- 读取 PRD:仅按索引/锚点抽取块(必须逐字原文复制)
前置条件(必须满足)
docs/PRD.md、docs/GLOBAL-CONTEXT.md、docs/story-$ARGUMENTS-*.md均存在且 Story 文件仅匹配 1 个- Story YAML front-matter 必须可解析,且
n == $ARGUMENTS
机械抽取规则(必须遵守)
A) 从 Story 抽取索引(只看 YAML front-matter)
对 docs/story-$ARGUMENTS-*.md 文件首部 --- ... ---:
- 抽取并去重排序(按编号升序):
S_fp = fp_ids[](FP-001)S_gc_br = refs.gc_br[](BR-001)S_prd_br = refs.prd_br[](BR-001)S_tbl = refs.prd_tbl[](TBL-001)S_api = refs.prd_api[](API-001)S_art = artifacts.file + artifacts.cfg + artifacts.ext(ART:*token)
B) 从 GC 抽取(避免通读)
- 必须逐字原文复制
- 固定复制以下 整段章节(按标题边界截取,
## X.到下一个##之前):## 2. 项目结构(必填)## 3. 枚举值定义(必填;无则写 N/A)## 5. 权限矩阵(必填)## 8. API规范(必填)
- 对于业务规则:仅从第 4 节规则表中复制被引用的
BR-###行(连同表头与分隔行;无引用写N/A) - 对于项目验证命令:从 GC 第 2 节
### 项目验证命令(如适用;否则写 N/A)的表格逐行抽取到 pack 的verification.commands(按表格顺序;不改写)- 若该小节为
N/A或表格不存在:verification.commands只写 1 行type/command/note均为N/A - 否则:对表格每一行数据,原文复制三列到
type/command/note- 若
command = N/A:该行type与note也必须为N/A - 若
command != N/A:该行type必须以gate:或opt:开头;不得为N/A
- 若
- 若该小节为
C0) FP→落点映射预检查(必须;兜底防硬违约)
- 在 PRD 中定位
### 8.0 功能点→落点映射(必填)表,抽取本 StoryS_fp对应行(表头 + 分隔行 + 行;按FP-001升序) - 对每个
FP-001的“落点”列:解析为集合(N/A或逗号分隔多项),允许项前缀仅:DB:/FILE:/CFG:/EXT:/N/A - 计算期望覆盖集合(去重):
E_tbl =所有DB:TBL-###转换为TBL-###(必须为具体数字)E_art =所有FILE:/CFG:/EXT:转换为ART:FILE:/ART:CFG:/ART:EXT:(token 精确匹配)
- 校验(任一不满足即
FAIL并停止,不输出 pack):E_tbl必须是S_tbl的子集(缺失则列出缺失项)E_art必须是S_art的子集(缺失则列出缺失项)
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.
- 5d ago First seen · 142 lines · 0 tokens per session scan A f5ad2210e335
story-pack 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 2,742 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.
finishwt
You are finishing a worktree task.
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.