fec-source-driven-development

fec-source-driven-development is a skill for Claude Code, Codex from bovinphang/frontend-craft. It costs 76 tokens per session (1,330 once invoked), scanned A, original, MIT.

A development practice that bases frontend decisions on the current project, official documentation, source code, and tests. It is especially concerned with behavior that changes between versions.

In plain words
What is it for?
Use it when selecting or upgrading frontend libraries, checking migrations, reviewing public interfaces, investigating version differences, and recording important decisions.
Why use it?
It reduces bugs caused by outdated tutorials, guessed framework behavior, or assumptions about browsers, packages, APIs, and build tools.

Skill for Claude CodeCodex

Part of the frontend-craft plugin — 56 skills, 11 commands, 14 agents, 5 hooks, 6 MCP servers shipped together

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 skills/bovinphang/frontend-craft/fec-source-driven-development
Any agent
npx skills add bovinphang/frontend-craft --skill fec-source-driven-development
Clone the repo
git clone --depth 1 https://github.com/bovinphang/frontend-craft

Made for: Claude Code, Codex.

Or install frontend-craft, the plugin that ships this one along with the rest of its 56 skills, 11 commands, 14 agents, 5 hooks, 6 MCP servers.

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 fec-source-driven-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/bovinphang/frontend-craft/fec-source-driven-development.svg)](https://agentmods.dev/skills/bovinphang/frontend-craft/fec-source-driven-development)
Your own site
<a href="https://agentmods.dev/skills/bovinphang/frontend-craft/fec-source-driven-development"><img src="https://agentmods.dev/badge/skills/bovinphang/frontend-craft/fec-source-driven-development.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,330 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 $0.00076 $0.01330
Opus 5 $0.00038 $0.00665
Sonnet 5 $0.00015 $0.00266
Haiku 4.5 $0.00008 $0.00133

Measured 4d ago against content hash 0680ca0416dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fec-source-driven-development 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.

localized/zh-CN/skills/fec-source-driven-development/SKILL.md · 88 lines

What it actually says

来源驱动开发

用途

在前端实现、评审和架构决策中优先依据项目内事实、官方文档和当前版本行为,避免沿用过时经验或未经验证的假设。

流程

  1. 判断是否需要查源

    • 涉及框架新版本、路由、渲染模式、缓存、构建工具、浏览器 API、包发布格式、鉴权协议或公共接口时必须查源。
    • 涉及项目约定时先读本仓库 README、配置、模板、已有实现、测试和迁移记录。
    • 只是稳定语言语法或明显局部重构时,可使用项目现有模式作为事实来源。
  2. 收集权威材料

    • 首选官方文档、规范、源码、release notes、migration guide、类型定义和项目内测试。
    • 第三方文章只能作为线索,不能作为最终依据。
    • 对快速变化的库记录包名、版本、文档日期或页面标题。
    • 当用户要求从本地知识库、项目资料库或 knowledge/ 目录回答问题时,先走本地知识检索,不使用网络搜索补事实。
  3. 提炼决策

    • 写清当前版本推荐做法、弃用做法、限制条件和迁移注意事项。
    • 对多个可行方案说明选择理由、兼容性、维护成本和回退方式。
    • 若文档和项目现状冲突,优先解释冲突并给出渐进调整,不直接推翻已运行系统。
    • 对依赖升级、框架迁移和公共 API 变化,记录 release notes、migration guide、版本范围、破坏性变更和回滚方案。
  4. 落到实现

    • 将外部行为隔离在适配层、配置层或小型工具函数中,避免在组件里散落版本假设。
    • 公共接口变化要保持命名、错误形状、默认值和兼容策略清晰。
    • 代码注释只记录非显而易见的来源约束,不粘贴大段文档。
  5. 验证假设

    • 用类型检查、最小复现、单元测试、组件测试、E2E、构建或浏览器验证证明关键假设。
    • 如果无法验证,报告不确定性、风险范围和需要用户或团队确认的信息。
  6. 留下轻量决策记录

    • 当结论会影响公共接口、依赖版本、目录规范或团队工作流时,补充 ADR/变更记录或交给文档同步流程。

本地知识检索

当用户指定本地知识库路径,或默认 knowledge/ 目录存在时,可用本流程回答资料库问题、抽取证据或辅助决策。

  1. 定位根目录

    • 用户明确指定路径时使用该路径。
    • 否则检查当前项目下 knowledge/ 是否存在;不存在时说明未找到默认知识库并请求路径。
    • 不用文件 glob 判断目录是否存在。
  2. 分层导航

    • 优先读取根目录和子目录中的 data_structure.md
    • 根据目录说明选择最相关的少量分支,不一次性遍历整个知识库。
    • 记录候选文件、主题、时间/版本范围和为什么相关。
  3. 渐进检索

    • Markdown、文本、日志:先用关键词搜索,再局部读取命中上下文。
    • PDF:处理前先确认可用工具和提取路线,优先提取到临时文本后再检索,避免把整份 PDF 打进上下文。
    • Excel:处理前先确认读取/分析路线,先看工作表、列名和少量样例,再按字段过滤或聚合。
    • 默认最多 5 轮关键词迭代;每轮根据已找到证据调整同义词、缩写和范围。
  4. 回答与溯源

    • 先给结论,再列文件路径、章节、页码、工作表或行号附近作为依据。
    • 证据不足时说明查过哪些路径、缺什么信息,以及用户如何缩小范围。
    • 不把知识库外的网络信息混入答案,除非用户另行要求查外部来源。

事实源优先级

优先级 来源 用途
1 项目内配置、测试、已有实现 判断本仓库真实约定
2 官方文档、源码、类型定义 判断当前推荐行为
3 标准规范、浏览器兼容数据 判断平台能力和兼容边界
4 Issue、讨论、第三方文章 辅助排查,不能单独定案

约束

  • 不凭记忆给版本敏感结论。
  • 不把过时教程当作当前最佳实践。
  • 不引用无法复核的来源作为关键依据。
  • 不为追新而改动稳定项目约定;必须说明收益和迁移成本。
  • 不在交付中复制长篇外部文档;只保留必要结论和链接或文件路径。
  • 不把“查过文档”停留在口头;版本敏感决策需要能追溯到具体版本、路径或官方页面。

预期输出

输出来源清单、版本或项目事实、决策结论、实现影响、验证命令和未决风险。若修改代码,关键行为应有测试或构建验证支撑。

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. 4d ago First seen · 88 lines · 76 tokens per session scan A 0680ca0416dd

Subscribe to this mod's changes

fec-source-driven-development is a skill published in the GitHub repository bovinphang/frontend-craft (21 stars, last pushed 3d ago), licensed MIT. It adds 76 tokens to every session and 1,330 once invoked, about $0.0004 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

brand-design

Brand-aware design system generator that acts as Head of Brand. Translates abstract brand language into a mathematically-validated, implementation-ready design system, writes creative-brief.md as the source of truth for all UI/UX in a project, and optionally compiles it to framework tokens (Tailwind v4 @theme, v3…

rfxlamia/pocketto · 146 tokens

deslop

去除中文网文里的 AI 味。当用户说正文"太像AI写的/有翻译腔/太工整/没人味/排比堆砌/读起来假"、嫌"无缘无故的修辞""引用奇怪跨度大/语域不一致"、嫌"重复的修辞句式""同义反复(他非常生气他怒了)""极端词太多(非常/极大)""莫名其妙的陈述句""句号当顿号""段落太对仗工整行数雷同",或要把 AI 稿改得像真人时使用。产出更口语、更有网感、风格统一的网文文字。.

tance-mang/chinese-webnovel-skills · 164 tokens

english

英文网文出海写作(Wattpad / Royal Road / Webnovel / Radish / KDP)。当用户要写英文小说、出海英文平台、把中文故事改写成英文原生(不是翻译腔)、问英文平台怎么写/选哪个、或要去掉英文里的"中国网文翻译腔/AI腔"时使用。按英文网文规则产出像当地作者写的英文。.

tance-mang/chinese-webnovel-skills · 100 tokens

modern-frontend-architecture

Use when starting, scaffolding, or reviewing the architecture of a web frontend, or making any frontend architecture decision — framework/stack choice, client-server data, state management, routing/URL state, styling and design systems, i18n/RTL, server-side logging/observability, or deploy target. Triggers on new…

Amir-Abushanab/modern-frontend-architecture · 114 tokens

official-article-ingest

Use when Sam wants to collect, save, translate, or reformat official source articles/blog posts/research/product announcements into the Obsidian vault, especially requests mentioning 官方文章, 官网排版, 原始排版, 美观, 收录, 1:1, 原文1:1, or 英文中文对照1:1. Preserve the source site's information architecture and visual hierarchy rather than…

codingSamss/all-my-ai-needs · 95 tokens

ai-translating-content

Translate text between languages with AI while preserving brand voice and terminology. Use when translating app copy to Spanish, localizing marketing content, multilingual support tickets, i18n with AI, machine translation with brand voice, translating product descriptions, localizing help docs, batch translating i18n…

lebsral/DSPy-Programming-not-prompting-LMs-skills · 97 tokens