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 skills/seed-forge/harness-ai-kit/devlab-web-engineeringnpx skills add seed-forge/harness-ai-kit --skill devlab-web-engineeringgit clone --depth 1 https://github.com/seed-forge/harness-ai-kitWhat 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 | $0.00167 | $0.04749 |
| Opus 5 | $0.00084 | $0.02374 |
| Sonnet 5 | $0.00033 | $0.00950 |
| Haiku 4.5 | $0.00017 | $0.00475 |
Grade A, and why
devlab-web-engineering 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 3d 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 — 315 lines — stays where its author put it; the contents beside it link to each section on GitHub.
devlab-web-engineering
Web / 前端工程化能力层。从工程化六域入手，覆盖项目初始化、构建、依赖、打包与交付、 运行环境与工程规范，按「语言 × 框架」路由到对应 Profile 执行，一站式交付可构建、 可打包、可部署的前端项目。
Capability Layer 定位：本技能是能力层，负责工程化原则、能力编排、Profile 与 工程质量要求；不承接完整用户需求，不重复造底层工具——优先复用社区 Skill / Reference / CLI / MCP 及现有 DevLab Capability（create-vue / create-vite / 框架官方文档等只引用不重写）。 UI/UX 品味、视觉操作、QA/测试、Contract、CI/CD 等独立领域能力不在此范围（见 Out of Scope 路由表）。
触发条件
需要输出 Web 技术、集成或安全架构图时，消费 base-diagram-ops 的 web、integration、security profile；本技能提供 Web 工程事实，不实现图布局或导出器。
- 用户说"初始化前端项目工程""配构建配置""帮我打包前端""工程化规范"
- 新项目需要工程化引导（识别语言×框架后路由到对应 profile）
- 现有项目构建/打包/容器化/微前端排障（构建失败、产物异常、镜像路径等）
- 从旧式打包（无锁文件 / CRA）迁移到现代模式（Vite / lockfile / pnpm）
devlab-project-bootstrapPhase 4 编排路由（前端项目工程化初始化）
输入参数
| 参数 | 必填 | 说明 | 示例 |
|---|---|---|---|
workspace |
否 | 项目工作目录（默认当前目录） | /workspace/my-web |
framework |
否 | 框架显式指定（默认自动识别） | vue / react |
workflow |
否 | 只跑指定流程（默认全流程） | bootstrap / build / packaging |
语言 × 框架识别路由
路由键 = 语言 × 框架 双维。先识别语言（决定工程基线），再识别框架（决定加载哪个 Profile）。
语言维度
| 语言 | 处理 |
|---|---|
| TypeScript（主线） | 默认基线，所有 profile 按 TS 工程标准（tsconfig 严格模式、类型检查入 lint） |
| JavaScript（兼容） | profile 内降级差异：JSDoc 替代类型、跳过 tsc 类型检查 |
| 其他（扩展位） | references 层预留说明；WASM 等后续版本再建 profile |
框架维度（识别信号）
| 识别信号 | 框架 | Profile |
|---|---|---|
package.json 含 vue / vue-router / @vue/cli-service / nuxt |
vue | profiles/vue.md |
package.json 含 react / react-dom / next |
react | profiles/react.md |
package.json 含 @angular/core / angular.json |
angular | references 引用层 |
| 多种并存 / 识别不到 | — | 进 Phase 0 D0 卡片让用户确认 |
构建工具（Vite 主线 / Webpack 兼容 / Next.js 等）在 profile 内 toolchain 层识别，不作为路由键。
工作流
Phase 0: 决策确认（内建） ← 关键分歧在此收敛（语言×框架/包管理器×工具链/端口/运行时/制品源/环境变量/编排）
↓ decisions
Phase 1: 工程化基线分析（内建）→ project_profile（框架、构建工具、依赖、容器现状）
↓ project_profile
Phase 2: 按路由键分发
├─ vue → profiles/vue.md（实战级：六域完整工作流 + 微前端场景层）
└─ react → profiles/react.md（模板级）
↓ 各 profile 执行 bootstrap / build / packaging 对应 workflow
Phase 3: 验证闭环（内建）→ verification_report（脚本验证 + 构建验证 + 启动探测）
What ships with it
36 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.
- CHANGELOG.md 2.5 KB
- config.defaults.yaml 1.1 KB
- decisions.yaml 602 B
- principles/build-reproducibility.md 718 B
- principles/dependency-governance.md 676 B
- principles/environment-consistency.md 1.0 KB
- principles/project-structure.md 1013 B
- profiles/react.md 1.9 KB
- profiles/react/REFERENCE-REACT.md 11 KB
- profiles/vue.md 5.5 KB
- profiles/vue/REFERENCE-MICRO-FRONTEND.md 2.0 KB
- profiles/vue/REFERENCE-PITFALLS.md 14 KB
- profiles/vue/REFERENCE-VUE.md 9.2 KB
- profiles/vue/scripts/.env.local.example.template 358 B
- profiles/vue/scripts/build.sh.template 674 B
- profiles/vue/scripts/common.sh.template 4.4 KB
- profiles/vue/scripts/dev.sh.template 1.6 KB
- profiles/vue/scripts/doctor.sh.template 1.1 KB
- profiles/vue/scripts/lint.sh.template 487 B
- profiles/vue/scripts/orchestrator.sh.template 880 B
- profiles/vue/scripts/run-acceptance.sh.template 4.2 KB
- profiles/vue/scripts/test.sh.template 479 B
- profiles/vue/toolchain/REFERENCE-VITE.md 1.1 KB
- profiles/vue/toolchain/REFERENCE-WEBPACK.md 1.0 KB
- README.md 1.3 KB
- references/community/COMMUNITY-REFERENCES.md 955 B
- references/REFERENCE-BUILD-TOOLS.md 14 KB
- references/REFERENCE-INDEX.md 1.1 KB
- references/REFERENCE-MONOREPO.md 15 KB
- references/REFERENCE-NODE-VERSION-MGT.md 13 KB
- references/REFERENCE-REGISTRY-STRATEGY.md 14 KB
- skill.json 4.6 KB
- USAGE.md 2.6 KB
- workflows/bootstrap.md 5.9 KB
- workflows/build.md 1.1 KB
- workflows/packaging.md 1.3 KB
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.
- 3d ago First seen · 315 lines · 167 tokens per session scan A 2046b21d77bc
devlab-web-engineering is a skill published in the GitHub repository seed-forge/harness-ai-kit (21 stars, last pushed 6d ago), licensed Apache-2.0. It adds 167 tokens to every session and 4,749 once invoked, about $0.0008 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.
Other skills, from other repositories
etsy-category-listing
Etsy category page scraper: given an Etsy category URL (e.g. https://www.etsy.com/c/jewelry) and optional page number, returns paginated product listings with listingId, shopId, title, url, image, salePrice, originalPrice, currency, rating, reviewCount, shopName, isAd, freeShipping, badge from category and subcategory…
human-approval
Request human approval before performing a SAFETY-CRITICAL, IRREVERSIBLE, or SCOPE-EXPANDING action — submit a structured context (action, scope, risk, consequence) plus options, then STOP the current turn. The platform redispatches the agent after the human decides. NEVER use for routine deliverables (writing docs /…
firebase-analytics
Use when logging analytics events, setting user properties, configuring default event parameters, building funnels, or adding screen-view tracking.
firebase-remote-config
Use when implementing feature flags, running A/B tests, setting parameter defaults, fetching/activating config, or enabling real-time config updates.
git-master
MUST USE whenever a task needs a commit or git-history investigation. Covers atomic commits, staging, commit-message style, rebase, squash, fixup/autosquash, blame, bisect, reflog, git log -S/-G, and questions like who wrote this or when was this added. Do not use for ordinary code edits unless the user asks for git…
prismer-evolve-record
Record the outcome of applying an evolution strategy. Use after resolving an error where prismer-evolve-analyze provided a recommendation, to feed back success or failure to the network.