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 skills add ryanzhao1011/workframe --skill requirement-archivinggit clone --depth 1 https://github.com/ryanzhao1011/workframeWrote 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/skills/ryanzhao1011/workframe/requirement-archiving)<a href="https://agentmods.dev/skills/ryanzhao1011/workframe/requirement-archiving"><img src="https://agentmods.dev/badge/skills/ryanzhao1011/workframe/requirement-archiving.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 5.1 | $0.00137 | $0.04305 |
| Opus 5 | $0.00068 | $0.02152 |
| Sonnet 5 | $0.00027 | $0.00861 |
| Haiku 4.5 | $0.00014 | $0.00430 |
Grade B, and why
requirement-archiving scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| `scripts/extract_assets.py` | `python "$(cat .claude/workframe-state/plugin-root.txt)/skills/requirement-archiving/scripts/extract_assets.py" <源目录> <工作目录>` | `inventory.md` 模态矩阵 / `text/` 逐文件正文 / `images/` 无损图片 / `link How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requirement Archiving 历史需求归档 Skill
前置依赖
- skill:
document-norms§1（归属矩阵）/ §2（frontmatter 与时间戳）/ §3（overview 三段制）/ §11（写作纪律 + 交付前自查） - 项目 PRD 框架
.claude/skills/prd-style/SKILL.md（章节结构 / 各章写法 / 标注习惯的项目层事实源，装机放入；缺失时 fallback 读 coretemplates/project-skills/prd-style/SKILL.md——与 prd-writer 同机制）+ prd-writerwriting-guide.md（通用写作纪律） - skill:
module-init（建骨架）与module-index-refresh（索引刷新）——作为被调用件，不重复其职责 - skill:
html-demo（Phase 6 原型校准的执行引擎，有 UI 的需求才需加载） projects/specs/_meta/taxonomy.md（tags 受控词表，如项目维护；缺失时 check_archive 自动跳过词表检查）- 环境依赖（仅 Phase 0 收料脚本）：docx / PDF / xls 解析需 6 个 Python 库，一次安装：
pip install python-docx pdfplumber pypdfium2 openpyxl xlrd Pillow缺库不中断收料——对应格式文件在 inventory 备注标「缺哪个库怎么装」，装完重跑即可
定位
外部异构原始资料 → modules/ 需求事实源 的唯一工作流。三个近亲的分工：
| skill | 输入 | 本 skill 的关系 |
|---|---|---|
migrate-to-modules |
项目内已有的 specs/ md | 不重叠——那是搬迁，这是重建 |
prd-writer |
新需求共识 | 复用其写作规范；工作流不同（归档无「澄清需求」阶段，只有「对账原文」） |
code-to-doc |
代码仓 | 互补——本 skill 建意图基线，code-to-doc 建实现现状 |
核心形态约定：已上线需求写成现状基线（frontmatter status: shipped、验收标准章改为「现状口径（回归参照）」checkbox）；未开发需求写成规划稿（draft）。PRD 正文只写当前生效的规格——废弃方案不进正文，过程性中间记录用完即删。
九段工作流（Phase 0-8）
0 收料冻结 → 1 通读建模 → 2 方案拍板 → 3 骨架与shared → 4 PRD回填 → 5 反向对账 → 6 原型校准 → 7 关联收口 → 8 审查清源
每阶段有门禁，过不了不进下一阶段。
Phase 0 收料冻结
- 跑
scripts/extract_assets.py <源目录> <工作目录>产出：文件清单、模态矩阵（文字/图片/表格/外链/二进制）、逐文件正文、全部内嵌图片（无损）、外链清单 <工作目录>= 项目临时加工区tmp/req-archive-<slug>/（不进 git）。它只是中转：Phase 4 回填时把选用图片从工作目录归位到资产包assets/，Phase 8 审查清源后随任务清理工作目录- 识别不可转写资产（.rp 原型、二进制模板等）与源内容已丢失项（如「点击图片查看完整表格」占位但无图）
- 门禁：丢失内容与可补外链第一时间问用户能否补源；原件处置方案（哪些归档哪些可删）此时初判，不在模态盘点前拍板删除
Phase 1 通读建模
- 通读全部正文提取；重建需求树（父子单、空壳单）与时间线
- 信源质量分级：同一内容多信源（如 TAPD PDF 压缩图 vs 原 docx 高清图）时登记配对，取最高质量源，低清版只做佐证
- 识别横切字典类内容（编码表 / 状态映射 / 语言口径）→ 预定为 shared 事实源
- 门禁：每份文件读过；高低清信源配对完成
Phase 2 方案拍板
- basic/sub 定位：对照常见 4 种切分范式（按能力面 / 按系统运行环节 / 与生产子系统 1:1 / 按能力链分层）选型
- 产出「文档 → 落点」映射表，每份原文标三类处理之一：整合出 PRD / 并入所属 PRD 变更历史（小优化单）/ 拆分并入多处（跨落点单）
- 汇总第一批口径冲突清单（新旧版本打架、图文不一致）
- PRD 框架依据一并进集中拍板：产出 PRD 默认按项目
prd-style；项目存量 PRD 风格趋同（≥3 份）而prd-style仍是出厂默认版时，提议先走 prd-writer §风格定制与萃取再回填 - 门禁：映射表 + 原件处置方案 + 冲突清单经 AskUserQuestion 集中拍板；不散落在写作过程中零碎问
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 165 lines · 137 tokens per session scan B 9d7900e0dfd7
requirement-archiving is a skill published in the GitHub repository ryanzhao1011/workframe (4 stars, last pushed 20d ago), licensed MIT. It adds 137 tokens to every session and 4,305 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
latex-setup
Use when the user wants to set up or troubleshoot a LaTeX environment, choose between biber and bibtex, install packages for a specific venue template, or configure compilation. Triggers on phrases like "setup latex", "biber vs bibtex", "latex compilation error", "install latex packages", "venue template", or "texlive…
knowledge-structures
A system for organizing notes into navigation pages, synthesis notes, and small standalone notes. A map of content is a note that links together related notes around one topic.
html-prototype
A method for creating single-file HTML mockups that open in a browser and follow a project's design tokens, such as its fonts, colours, spacing, corners, and shadows.
feature-acceptance
A browser-based acceptance testing process that compares an online implementation with a product requirements document and, when available, an HTML prototype. It records what is complete, partial, missing, or inconsistent, with screenshots and prioritized blockers.
prd
A skill for writing and reviewing product requirements documents, or PRDs: documents that describe what a product or feature should do. It covers structure, fields, rules, edge cases, metrics, page layouts, and related system or algorithm flows.
gbg
Convert any plan, PRD, feature idea, or brief into a sequenced goal-by-goal execution document with reviewer-gated commits — for everyday feature development, MVPs, migrations, refactors, and hardening alike. Generates a project brief, per-goal scope/tasks/acceptance criteria, an LLM-reviewer prompt (Codex/etc.), a…