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-contextnpx skills add seed-forge/harness-ai-kit --skill devlab-web-contextgit 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 | $0.00087 | $0.01980 |
| Opus 5 | $0.00044 | $0.00990 |
| Sonnet 5 | $0.00017 | $0.00396 |
| Haiku 4.5 | $0.00009 | $0.00198 |
Grade A, and why
devlab-web-context 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 2d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
devlab-web-context — 前端项目上下文理解规则资产
<domain>-context家族（web/srv/infra/tool）首个成员。只提供 Understand Capability： 规定"什么时候理解、理解什么、理解到什么程度"，产出前端 context 画像，不生产五件套台账。
定位与边界
- 本技能是什么：web 域前端项目上下文理解规则（信号表 + 特有条目 + 渐进式理解工作流）。
- 本技能不是什么：不生产
.harness/devlab/五件套台账（那是devlab-context-bootstrap的职责）；不是工程化能力层（那是devlab-web-engineering）；不自建 CLI（社区 CLI/MCP/Skill 引用策略见 bootstrap 通用层）。 - 家族化：与未来的
devlab-srv-context/devlab-infra-context/devlab-tool-context同构——共享 bootstrap 通用层（四原则全文 + 社区引用 + 五件套骨架），本技能只承载 web 领域规则。
四原则（一句话摘要）
完整原则全文在
devlab-context-bootstrap（缺失时本摘要可独立指导行为）。
- context-before-change：改动任何代码前先建立最小上下文，禁止在未知项目状态下动手。
- evidence-before-assumption：画像条目只写实证（读到的配置/跑通的命令）；推断必须标注依据；未验证标
todo。 - progressive-understanding：按需加深，最小上下文起步，置信度不达标才 Deepen，不做一次性全量理解。
- re-understand：执行中发现认知偏差（命令跑不通/现象与画像不符）立即回退重理解，不将错就错。
双模式入口
模式 A：规则包模式（被 bootstrap 委托）
触发方：devlab-context-bootstrap Phase 0 判定 frontend-web 后。
执行：
- 判定前端子类型（信号文件）：有
qiankun/micro-app/自研 shell 注册配置 →vue-microfrontend；有react+ SPA 结构 →react-spa；默认vue-microfrontend（当前实证最全）。 - 读取
profiles/<profile_type>.md（子类型特有信号与条目）+references/REFERENCE-WEB-RULES.md（跨子类型通用信号）。 - 按信号表扫描项目，逐条产出画像维度（key/value/confidence/evidence/note）。
- 画像写入
.harness/devlab/context/<project>-web-context.yaml（契约见下文）。 - 返回给 bootstrap：画像路径 + 概要（profile_type / overall_confidence / 主要发现）。
模式 B：完整工作流模式（独立自编排）
触发：用户直接要求"理解这个前端项目 / 生成前端 context 画像"。
工作流（四步循环）：
Task
↓
Identify Scope # 项目根、子应用清单（monorepo 逐个）、理解目的（改代码/排障/验收）
↓
Build Minimal Context # 读 profiles/<type>.md + REFERENCE-WEB-RULES → 最小信号扫描
↓
Confidence Check # 每条目标 confidence：confirmed 需 evidence；不足 → Deepen
↓
足够理解 → 产出画像并结束
不足 → Deepen Context # 读更多配置/跑命令/查注册配置
认知偏差 → Re-understand # 回退重扫，更新画像
结束条件：所有关键键达到 confirmed 或 inferred（无未解释的 todo 阻塞），或资源上限（扫描轮次/时间）。
产出：前端 context 画像（契约见下）。需落台账时 → 委托 devlab-context-bootstrap（镜像衔接：bootstrap 消费画像填五件套）。
What ships with it
9 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.
- 2d ago First seen · 124 lines · 87 tokens per session scan A 8e2dec53840c
devlab-web-context 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 87 tokens to every session and 1,980 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.
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.