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 yike-gunshi/forge-skills --skill forge-feature-docgit clone --depth 1 https://github.com/yike-gunshi/forge-skillsWrote 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/yike-gunshi/forge-skills/forge-feature-doc)<a href="https://agentmods.dev/skills/yike-gunshi/forge-skills/forge-feature-doc"><img src="https://agentmods.dev/badge/skills/yike-gunshi/forge-skills/forge-feature-doc/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/skills/yike-gunshi/forge-skills/forge-feature-doc"><img src="https://agentmods.dev/badge/skills/yike-gunshi/forge-skills/forge-feature-doc.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 | $0.00265 | $0.03284 |
| Opus 5.5 | $0.00106 | $0.01314 |
| Sonnet 5.5 | $0.00053 | $0.00657 |
| Haiku 4.5 | $0.00026 | $0.00328 |
Grade A, and why
forge-feature-doc 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 6d 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.
forge-feature-doc — 每个功能一份给人看的需求设计文档
交付 docs/modules/<功能>.md 和它的图（docs/assets/visuals/<英文短名>/overview/）：开头是待拍板，按需写 12 个部分，先图后字，只写当前设计，末尾记关键改动。配套三个脚本：出示意图、给真实页面截图加标注、上线前检查。
定位与边界
像一个会画图的产品搭档——把「这个功能长什么样、按什么规则跑、效果由哪些数决定、还缺你哪些决定」讲透：先放图，再用一两行字注释，不把 PRD、DESIGN 换个说法再讲一遍。
核心立场：读者是要拍板、注意力有限的人（按 ADHD 友好来写）。forge 产出的 PRD、DESIGN、feature-spec 是写给 AI 执行的，必然很长，读者审不过来，迭代中改了什么也看不到，文档和代码就一路漂移。所以这份文档只写当前设计里决定九成效果的内容，固定顺序、按需取舍，每部分先图或表；历史只留末尾 15 条关键改动；凡是改变效果的改动，都要在这里留下痕迹。
边界之外的交出去：写给 AI 的 PRD、feature-spec 交 forge-prd；DESIGN.md 文字规格和 token 表交 forge-design；在真比例骨架上定布局交 forge-design-lab；写或改 prompt 本身交 prompt-craft；写代码交 forge-eng；进度交 forge-status；复盘交 forge-fupan。对外文章、发布公告不在范围。
一次只处理一个功能。
按需读取
| 文件 | 什么时候读 |
|---|---|
references/writing-rules.md |
新建前；第一次在某个项目里更新前（12 个部分各写什么、怎么展示、ADHD 写法、只写现在） |
references/stage-map.md |
被某个 forge 阶段调用、要判断改哪几部分时 |
references/visuals.md |
出图前（示意图模板、截图脚本写法、标注约定、踩坑） |
references/example-ai-search.md |
第一次在新项目里用、想看完整范例时 |
意图分流
| 意图 | 信号 | 应答 |
|---|---|---|
| 新建 | docs/modules/<功能>.md 不存在 |
走「新建」全流程 |
| 阶段更新 | 文档已存在；来自某阶段收尾，或用户说「更新」并指出改了什么 | 走「更新」，只动受影响的部分 |
| 出图 | 「截图」「示意图」「重拍」「图过期了」 | 只走「出图」 |
| 检查 | 「上线前」「检查文档」，或 forge-review / forge-ship 调用 | 只走「检查」 |
| 潜在 | 用户抱怨文档太长看不懂、调整看不到，但没要求出文档 | 一句话说明能做什么，问要不要建；不自动开工 |
工具
{skill} 指本 skill 目录。scaffold 会把另外三个脚本复制到项目的 scripts/design-doc/，项目里没装本 skill 也能跑。
| 脚本 | 什么时候 | 用法 | 失败降级 |
|---|---|---|---|
scaffold.mjs |
新建 | node {skill}/scripts/scaffold.mjs --repo <仓库> --feature <功能名> --slug <英文短名> --types ui,backend,ai |
— |
render-diagrams.mjs |
改了 overview/src/*.html |
NODE_PATH="$(npm root -g)" node scripts/design-doc/render-diagrams.mjs <overview 目录> |
没有 Playwright：只交 HTML 源文件，说明图待补 |
annotate.mjs |
写项目截图脚本时引用 | 见 references/visuals.md |
本地服务没起：用设计骨架页面截图 |
check.mjs |
每次改完；review / ship 门禁 | node scripts/design-doc/check.mjs [基准分支] |
报错先在已知健康的文档上验证脚本，再信结果 |
新建
- 读资料：项目
docs/README.md的文档规则（没有就跳过），再读 PRD、feature-spec、讨论稿、已有的长文档。只取决定效果的事实；数值以代码和配置为准，文档和代码对不上时以代码为准并记下。 - 判类型：有没有界面、有没有后端、有没有 AI 或算法，决定写哪几部分（对照表在
writing-rules.md）。判断不了就问一句。 - 建骨架：跑
scaffold.mjs。 - 填内容：照
writing-rules.md写。还没定的进「待你拍板」并标 ⚠️；定了还没做的标 ⏳。关键改动从 git log 和 CHANGELOG 里挑影响效果的补齐（最多 15 条），理由查不到就写「理由未记录」。 - 出图：现状和流程两张示意图必出。有界面的：设计阶段用 forge-design-lab 骨架截图，实现后用真实页面截图加标注；两者都截不到时画页面示意（
page-mock.html），不画只有方框的线框。 - 检查、打开、汇报：跑
check.mjs，用open -a "Visual Studio Code" <文档>打开（无界面运行时跳过），在对话里按下面的格式汇报。
What ships with it
17 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.
- assets/diagrams/architecture.html 960 B
- assets/diagrams/diagram.css 1.9 KB
- assets/diagrams/flow.html 964 B
- assets/diagrams/funnel.html 1010 B
- assets/diagrams/page-mock.html 3.6 KB
- assets/diagrams/pipeline.html 1023 B
- assets/diagrams/status-quo.html 629 B
- assets/doc-template.md 2.9 KB
- README.md 2.1 KB
- references/example-ai-search.md 1.9 KB
- references/stage-map.md 2.9 KB
- references/visuals.md 6.6 KB
- references/writing-rules.md 9.1 KB
- scripts/annotate.mjs 4.3 KB runs code
- scripts/check.mjs 7.0 KB runs code
- scripts/render-diagrams.mjs 1.4 KB runs code
- scripts/scaffold.mjs 3.5 KB runs code
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.
- 6d ago First seen · 142 lines · 265 tokens per session scan A 74f173cbcfb7
forge-feature-doc is a skill published in the GitHub repository yike-gunshi/forge-skills (13 stars, last pushed 2d ago), licensed MIT. It adds 265 tokens to every session and 3,284 once invoked, about $0.0011 per session on Opus 5.5. 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 2026-10-11.
Other skills, from other repositories
vastai
Vast.ai CLI to manage GPU instances, volumes, serverless endpoints, and billing.
vastai-sdk
Vast.ai Python SDK — high-level API for GPU instances, volumes, serverless endpoints, and billing.
forge-evolution
Autonomous persona evolution pipeline for failure-driven capability growth.
docs-context
Super Base Context — project doc loader & synchronizer. Triggers even without explicit "load docs"/"sync docs." READ MODE — load architecture/modules/coding/decision docs when work references project state: code work (write/modify/remove); design (features/APIs/schemas/architecture); review (modules, past solutions)…
houtu-dependencies
Skill "houtu-dependencies" from lujiafa/houtu-project-skills, covering houtu framework — ai agent coding guide, core principles, code generation workflow (must be executed in order), step 1 — detect version & dependencies and step 2 — identify scenario & select module.
senzing-entity-resolution
Guides AI agents through Senzing entity resolution workflows using the Senzing MCP server. Covers data mapping to Senzing format, SDK code generation (Python, Java, C#, Rust, TypeScript/Node.js), documentation search, error troubleshooting, sample data access, reporting and visualization, SDK setup guides, and…