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/prd)<a href="https://agentmods.dev/commands/snakeying/textum/prd"><img src="https://agentmods.dev/badge/commands/snakeying/textum/prd/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/prd"><img src="https://agentmods.dev/badge/commands/snakeying/textum/prd.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 | $0.02063 |
| Opus 5.5 | $0.00000 | $0.00825 |
| Sonnet 5.5 | $0.00000 | $0.00413 |
| Haiku 4.5 | $0.00000 | $0.00206 |
Grade A, and why
prd 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
阶段1b: PRD 生成/修正
只做一件事：把 plan-pack 落盘为 PRD（按模板）。
约束：本命令不做需求对话。若信息不足以生成“可检查的 PRD”，输出
PRD_PLAN_CLARIFY_PACK并停止（不修改任何文件）。
读取：docs/prd-plan-pack.yaml +（如存在）docs/PRD.md | 写入：docs/PRD.md（信息不足则不写） | 模板：.claude/textum/PRD-framework.md | 可选输入：FAIL/DECISION 清单
输入
- plan-pack（唯一事实来源；不得向用户索要整包粘贴）
- （可选）
FAIL/DECISION清单（用于精准修正）
修正模式（当提供 FAIL/DECISION 清单时必须遵守）
- 以现有
docs/PRD.md为基线：只修改清单命中的位置，其余内容不做无关改动（最小 diff） - 稳定 ID/锚点禁止漂移：不得重排/重编号；若必须新增，只能在末尾新增并按序递增
- 若清单需要补充事实且 plan-pack 不足以支撑：输出
PRD_PLAN_CLARIFY_PACK并停止（不写文件）
输出
二选一（必须遵守）：
- 成功：创建/更新
docs/PRD.md（不含任何模板占位符），并输出：PASS已写入：docs/PRD.md下一步：/prd-check
- 信息不足：输出
PRD_PLAN_CLARIFY_PACK代码块后，追加两行纯文本指引（不修改任何文件）：下一步：复制 PRD_PLAN_CLARIFY_PACK 粘贴给 /prd-plan重跑：/prd
PACK 完备性校验（必须）
docs/prd-plan-pack.yaml是唯一事实来源：PRD 只能从已确认字段映射出来（不得脑补）- 必须满足最小可用性：
modules至少 1 个，且至少 1 个模块priority = P0business_rules至少 1 条且每条非空
- 对照
.claude/textum/PRD-framework.md的必填章/表逐项校验：必须能完整填满且不残留任何占位符（如TBD、[...]、[field]、[METHOD]、[PATH]、[table]、PRD#API-###、PRD#TBL-###） - PRD
7.3 命名规范：- 仅当 plan-pack
assumptions_constraints[].assumption_or_constraint中存在以命名规范:开头的已确认约定时才写表格 - 否则该小节正文仅一行
N/A（不追问、不阻断）
- 仅当 plan-pack
- 必须可闭合“功能点→落点映射”（PRD
8.0）：- pack 来源：
modules[].feature_points[].landing（不可为空；不明确就回PRD_PLAN_CLARIFY_PACK） - pack 中每条
landing允许值：N/A或逗号分隔多项集合（不改写 token 本体）：DB:<table>：数据库表（<table>必须能在data_model.tables[].table中找到）FILE:<path/glob>：文件/目录/生成产物（允许包含如/posts/[slug]等路由/通配片段）CFG:<key>：配置项/开关/参数EXT:<system>：外部依赖
- PRD 输出规范：
DB:<table>必须映射为DB:TBL-###（TBL-001起连续）并能在 PRD8.2用锚点<!-- PRD#TBL-### -->唯一定位 - 若
data_model.tables为空：PRD8.1/8.2/8.3均写N/A，且 PRD8.0不得出现任何DB:落点
- pack 来源：
- 仅当无法生成“可检查的 PRD”时才输出
PRD_PLAN_CLARIFY_PACK并停止（不写文件）；阻断条件包括：- plan-pack 不满足最小可用门禁（例如：
api.has_api=null、缺模块/缺功能点/缺落点、缺规则、缺权限矩阵等） - 任何必填表格/章节只能靠猜测才能补齐
- 无法闭合
8.0 功能点→落点映射（含落点 token 不合法、或DB:<table>找不到data_model.tables[].table） api.has_api=true但api.endpoints无法提供最小清单（method/path/permission/summary）- 需要新增 API/TBL 但缺少最小可定位信息，无法保证 ID/锚点稳定
- plan-pack 不满足最小可用门禁（例如：
- 其余“非阻断缺失”（例如：第 2.3/7.1/7.2/10 细节不足、表字段不全、错误码不全）：用
N/A/None明确落盘，不追问、不阻断
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 · 98 lines · 0 tokens per session scan A 74ea5123453d
prd 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 2,063 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.