story-pack

story-pack is a command for Claude Code from snakeying/Textum. It costs 0 tokens per session (2,742 once invoked), scanned A, original, MIT.

A command that creates a YAML execution pack for one numbered software work item, called a Story.

In plain words
What is it for?
Use it to validate the Story’s source files, extract its relevant project rules and requirements, and write an execution pack when checks pass.
Why use it?
It gathers the required instructions and references into one small input file, reducing the need to reread larger project documents during implementation.

Command for Claude Code

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/story-pack
Clone the repo
git clone --depth 1 https://github.com/snakeying/Textum

Made for: Claude Code.

Wrote 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.

agentmods badge for story-pack

README.md
[![agentmods](https://agentmods.dev/badge/commands/snakeying/textum/story-pack.svg)](https://agentmods.dev/commands/snakeying/textum/story-pack)
Your own site
<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>
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 2,742 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.

ModelPer sessionOnce 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

Measured 5d ago against content hash f5ad2210e335, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

outdated/.claude_outdated/commands/story-pack.md · 142 lines

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-$ARGUMENTS-*.mddocs/GLOBAL-CONTEXT.md(只读)、docs/PRD.md(只读) | 写入:docs/story-$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。

  1. 读取 Story:仅解析 YAML front-matter 作为索引
  2. 读取 GC:按索引抽取片段(固定章节 + 规则表行 + 验证命令表)
  3. 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.mddocs/GLOBAL-CONTEXT.mddocs/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)

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.extART:* 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
      • command = N/A:该行 typenote 也必须为 N/A
      • command != N/A:该行 type 必须以 gate:opt: 开头;不得为 N/A

C0) FP→落点映射预检查(必须;兜底防硬违约)

  1. 在 PRD 中定位 ### 8.0 功能点→落点映射(必填) 表,抽取本 Story S_fp 对应行(表头 + 分隔行 + 行;按 FP-001 升序)
  2. 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
  3. 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)
  4. 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)

Read the full file on GitHub · 142 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.

  1. 5d ago First seen · 142 lines · 0 tokens per session scan A f5ad2210e335

Subscribe to this mod's changes

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.