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 taxueseek/argo --skill ego-searchgit clone --depth 1 https://github.com/taxueseek/argoWrote 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/taxueseek/argo/ego-search)<a href="https://agentmods.dev/skills/taxueseek/argo/ego-search"><img src="https://agentmods.dev/badge/skills/taxueseek/argo/ego-search/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/taxueseek/argo/ego-search"><img src="https://agentmods.dev/badge/skills/taxueseek/argo/ego-search.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00257 | $0.03873 |
| Opus 5.5 | $0.00103 | $0.01549 |
| Sonnet 5.5 | $0.00051 | $0.00775 |
| Haiku 4.5 | $0.00026 | $0.00387 |
Grade A, and why
ego-search 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 1mo 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ego-search（argo 子技能）
ego-search 是 argo 的登录态专业搜索子技能（v1.4 完全态）：
- 双运行时保留：ego lite（
ego-browser）与 WebBridge（用户浏览器扩展桥）互补，不互相替代 - 任一可用即可：
search/fetch/act/api在至少一条运行时在线时可用 - 与常规检索隔离：登录态结果
cache_eligible=false，禁止进公共 SearchCache - 汇总可融合：输出带
merge_with_public_ok=true，分析层可把 public + login 两路结果一起喂 evidence
专业搜索模式（默认关闭）
本子技能涉及真实浏览器登录态继承，出于安全与可靠性考虑默认关闭。开启后
search/fetch/act/api 与直接浏览器操作才可用；未开启时调用会被拒绝并提示开启命令。
# 开启（必须由用户明确要求「开启专业搜索模式」后执行）
python3 sub-skills/ego-search/scripts/ego_search.py enable
# 关闭
python3 sub-skills/ego-search/scripts/ego_search.py disable
# 查看状态
python3 sub-skills/ego-search/scripts/ego_search.py status
- 纪律：Agent 不得自行开启——只有用户明确表达开启意图时才运行
enable。 - 未开启时，同样不得用 heredoc 直连浏览器运行时绕开闸门。
- 状态持久化于
~/.local/state/ego-search/pro-mode.json，开启后长期生效，直到手动关闭。
定位与升级决策
主系统 API/HTML 检索覆盖不足时，升级到 ego-search：
| 场景 | 常规检索 | ego-search 补什么 |
|---|---|---|
| 登录墙内容（知乎/小红书/微博/X/公众号/会员站） | 拿不到正文 | 任务空间继承登录态，搜并抓取 |
| JS 渲染 / SPA / 懒加载页面 | 可能空壳 | 真实浏览器执行 JS 后提取 |
| 反爬 / Cloudflare 保护（尽力而为） | HTTP 失败 | 真实浏览器尝试，重度防护可能失败 |
| 需要交互的动态搜索（翻页/「加载更多」/表单筛选） | 单次请求不够 | act 或 ego-browser heredoc 多步 |
| 搜索引擎实时 SERP（Google/Bing/百度） | 可能被反爬 | 真实 SERP 结构化提取 |
| 深嵌套 iframe 页面 | 常挂 | 快照专长 |
| 已知同源 API URL | DOM 不全 | api + browserFetch |
| 未知 XHR 尚未拿到 URL | — | 不在 CLI 内；heredoc 自探或先拿 URL 再 api |
决策顺序：
常规检索（快、省 token）
→ 结果不足 / 正文拿不到 / 需要登录态
→ ego-search search|fetch|act|api（pro-mode 开启）
→ 更复杂多步 → ego-browser nodejs heredoc
高后果结论 → 证据核验
依赖与环境
- 官方项目：ego lite → https://lite.ego.app/（官网）；WebBridge → https://www.kimi.com/zh-cn/help/kimi-webbridge/kimi-webbridge-introduction（Kimi WebBridge 官方帮助中心）。
- 浏览器运行时（macOS 应用）与 运行时命令
ego-browser（~/.local/bin）。 - 首次使用前确认：
command -v ego-browser。未安装时按references/install.md完成安装。 - 运行时依赖由安装包自管理，本子技能不重复携带安装脚本。
- 登录态来自运行时 onboarding（可导入 Chrome 数据）；不同站点登录态由用户在运行时中维护。
快速开始（ego_search.py CLI）
What ships with it
11 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.
- references/browser-runtime.md 2.5 KB
- references/install.md 3.1 KB
- references/original-ego-upgrade.md 1.5 KB
- scripts/ego_search.py 30 KB runs code
- scripts/merge.py 8.3 KB runs code
- scripts/quality.py 2.2 KB runs code
- scripts/runtime.py 5.9 KB runs code
- scripts/safety.py 3.3 KB runs code
- scripts/serp_spec.py 5.1 KB runs code
- scripts/webbridge_adapter.py 13 KB runs code
- tests/test_query_normalize.py 2.7 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.
- 1mo ago Changed · -118 lines · +23 tokens per session f8448e07f110
- 2mo ago First seen · 372 lines · 234 tokens per session scan A 163a89748b54
ego-search is a skill published in the GitHub repository taxueseek/argo (226 stars, last pushed 3d ago), licensed Apache-2.0. It adds 257 tokens to every session and 3,873 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
pentest-playbook
A penetration-testing playbook for examining authorized websites, applications, and services for real, verified security weaknesses.
browser-skill
Automate the user's logged-in Chromium browser: read pages, fill forms, scrape data, operate tabs, test a UI, or debug a website. Requires the bsk CLI and browser extension.
lingshu-browser
A routing guide for browser and web-development topics, including rendering, the DOM, event loops, web storage, content security, performance, and progressive web apps. It directs a task to a more specific unit when needed.
browser-440d4398
A browser popup controller that allows popups started by a user action and blocks and records automatic popups.
browser-02898b15
A narrowly targeted browser skill for event bubbling, where a browser event travels from the element that received it up through its parent elements. It is intended only when the task explicitly concerns this event path.
browser-0754386d
A guide to the browser Fetch API, which sends network requests with a method, URL, headers, and optional body.