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/storygit 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)<a href="https://agentmods.dev/commands/snakeying/textum/story"><img src="https://agentmods.dev/badge/commands/snakeying/textum/story.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 | $0.00818 |
| Opus 5 | $0.00000 | $0.00409 |
| Sonnet 5 | $0.00000 | $0.00164 |
| Haiku 4.5 | $0.00000 | $0.00082 |
Grade A, and why
story 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 4d 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.
What it actually says
阶段6: Story 执行
$ARGUMENTS: Story 编号（如: 1）
读取：docs/story-$ARGUMENTS-exec-pack.yaml（唯一事实来源；必须存在） | 写入：仓库文件（代码/测试；仅本 Story） | 模板：N/A
若 pack 文件不存在：停止并提示用户先运行 /story-pack $ARGUMENTS 写入 pack 文件。
硬约束
- 只做本 Story；严格按 pack 内容实现；不发明 pack 外的新规则/新接口/新字段
docs/story-$ARGUMENTS-exec-pack.yaml是唯一事实来源：禁止再读取/通读docs/PRD.md、docs/GLOBAL-CONTEXT.md、docs/story-*.md- pack 缺失/矛盾/不可执行：停止并输出清单（每条必须包含：定位 / 问题 / 期望 / 影响 / 修复；只给 1 个动作；通常为“修正来源文档后重跑
/story-pack $ARGUMENTS”）
执行步骤（必须按序）
- 解析
docs/story-$ARGUMENTS-exec-pack.yaml：提取功能点、依赖、规则、数据/产物落点、接口、验收标准、测试要求、验证命令（包含prd.fp_artifact_rows） - 若声明“前置Story/已有资源”：在仓库中检索，只读取必要签名（避免重复实现）
- 实现：按验收标准最小改动完成需求，并补齐测试要求
- 验证（以“最终产出符合用户预期”为准；避免为 lint 等非阻断项过度返工）：
- 将
verification.commands按type分为两类（不改写命令本身）：gate:*：门禁验证（失败需修复并重跑直到通过）opt:*：可选验证（失败只记录DECISION，不影响交付）
type = N/A或command = N/A的行：视为不可执行，跳过- 执行顺序：先跑所有
gate:*，再跑opt:* - 若不存在任何可执行的
gate:*（全部为N/A或仅有opt:*）：不输出DECISION；仅按验收标准做人工验证/自检并在输出中写明
- 将
- 输出（低噪；不得粘贴大段代码/日志）：
完成情况（人工验收清单）：逐条列出 Story## 验收标准的- [ ]项，并标记DONE/NOT_DONE（若有未完成必须说明阻塞原因）关键变更：仅列“应改动的关键文件路径 + 1 句职责/变化”，不贴 diff验证结果：逐条列出执行过的gate:*/opt:*命令与结论（PASS/FAIL）；失败仅给 1 句摘要 + 下一步动作（若无可执行gate:*：写gate:*: N/A）DECISION：仅在需要用户确认时输出（例如：opt 失败但可交付、或 pack 信息不足需回补）下一步：除非用户明确指定下一条 Story 编号，否则写N/A（禁止推断下一条 Story）
开始
请提供 Story 编号（例如：/story 1）。
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.
- 4d ago First seen · 37 lines · 0 tokens per session scan A 510fbc7961aa
story 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 818 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.
project
Manage projects: register repos, inspect, configure per-project settings, and remove.
vibe-workflow
The vibe-coding workflow turns an app idea into a working MVP in 5 stages. Your job: figure out where the user is and route them to the right stage.
pm-done
Close a todo (TODO-xxx), sync completed.md, refresh overview.
pm-status
Show governance health, wizard next step, all open blocking/high todos, and pending review count. Primary daily entry.
pm-charter
Create, import, discover, approve, or skip project charter. No-arg form is an interactive wizard.