Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add aAAaqwq/AGI-Super-Team/plugin install agi-super-teamWrote 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/aaaaqwq/agi-super-team/auth-manager)<a href="https://agentmods.dev/skills/aaaaqwq/agi-super-team/auth-manager"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/auth-manager/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/aaaaqwq/agi-super-team/auth-manager"><img src="https://agentmods.dev/badge/skills/aaaaqwq/agi-super-team/auth-manager.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 | $0.00035 | $0.01779 |
| Opus 5 | $0.00017 | $0.00890 |
| Sonnet 5 | $0.00007 | $0.00356 |
| Haiku 4.5 | $0.00003 | $0.00178 |
Grade A, and why
auth-manager scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**优先级:curl/CLI > 内置 browser** How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auth Manager v4.0 — 平台登录态管理
统一使用 OpenClaw 内置 browser (profile=openclaw),所有平台共享同一个 Chrome profile。 ⚠️ 禁止使用 fbu / fast-browser-use,已废弃。
架构 — 单一 Profile 模型
~/.openclaw/browser/openclaw/user-data/ ← 唯一的 Chrome profile(内置 browser)
~/.openclaw/auth-platforms.json ← 平台配置
~/.openclaw/auth-session-state.json ← 检查结果状态
为什么统一?
- 所有 agent(quant/ops/main 等)共享同一 browser profile
- 一次登录,全部可用。不存在"这个 agent 没登录"的问题
- OAuth 链式登录(如Provider-A 依赖 GitHub)自动继承
核心职责
职责 1: 检查登录态(定期 cron)
优先级:curl/CLI > 内置 browser
方法 A: curl/CLI 检查(快速、不占资源)
# GitHub — 最可靠
gh auth status 2>&1
# AIXN — curl API
TOKEN=$(python3 -c "import json; print(json.load(open('/home/aa/.openclaw/chrome-profiles/provider-session.json')).get('token',''))" 2>/dev/null)
curl -s --max-time 10 'https://ai.9w7.cn/api/user/info' -H "Authorization: Bearer $TOKEN"
# Provider-A — curl
COOKIE=$(python3 -c "import json; print(json.load(open('/home/aa/.openclaw/chrome-profiles/your-provider-session.json')).get('cookie',''))" 2>/dev/null)
curl -s --max-time 10 'https://your-provider.example.com/api/user/info' -H "Cookie: $COOKIE"
方法 B: 内置 browser 检查(需要渲染的站点)
# 导航到目标页面
browser(action='navigate', targetUrl='<check_url>', profile='openclaw')
# 等待加载后截取快照
browser(action='snapshot', compact=true, maxChars=2000, profile='openclaw')
适用平台:Polymarket、LinuxDo、X、抖音、小红书
判定逻辑:
- 快照包含
logged_in_indicators关键词 → ✅active - 快照包含
login_page_indicators关键词 → ❌expired - 超时/网络错误 → ⚠️
error(不是 expired!区分清楚)
职责 2: 新平台授权
当需要为新平台登录时:
# 1. 用内置 browser 打开登录页
browser(action='navigate', targetUrl='https://platform.com/login', profile='openclaw')
# 2. 截图给用户确认页面
browser(action='screenshot', profile='openclaw')
# 3. 如果需要用户操作(扫码等),等待用户确认后再 snapshot 验证
browser(action='snapshot', compact=true, profile='openclaw')
登录成功后,cookie/localStorage/IndexedDB 自动保存在 ~/.openclaw/browser/openclaw/user-data/。
职责 3: 其他 agent 使用登录态
所有 agent 调用内置 browser 时自动继承登录态:
What ships with it
1 file 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.
- 3d ago First seen · 169 lines · 35 tokens per session scan A 1cc404bd3fc1
auth-manager is a skill published in the GitHub repository aAAaqwq/AGI-Super-Team (91 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 1,779 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
browser-check
Drive a real browser and come back with a MEASUREMENT rather than an impression - console errors and >=400 responses as counts, computed styles as JSON when appearance is disputed. Use when work touches UI, when a review must verify one, or when fidelity-gate asks for its measurement.
qa
QA testing skill with real browser automation. Use when asked to "test this site", "QA this page", "check for visual bugs", "verify the deploy", or when Hydra needs browser validation for UI changes. Requires the browse binary.
chrome-devtools
Drive the machine Chrome debug browser via OpenClaw-managed MCP (chrome-devtools). Use for page navigation, snapshots, screenshots, clicks, forms, console/network inspection — not for host shell risk.
mission-control
Interact with Mission Control — AI agent orchestration dashboard. Use when registering agents, managing tasks, syncing skills, or querying agent/task status via MC APIs.
browser
Browser automation via the agent-browser CLI. Use when the user needs to drive websites or Electron desktop apps — navigating, filling forms, clicking, screenshots, extracting data, testing web apps, visual UI checks, the Pi Dashboard's Electron shell, or the user's own logged-in browser (SSO/2FA sites). Triggers…
prompt-tuning
Tune a prompt, or anything whose quality is measured by non-deterministic model output, without chasing noise - a noise baseline before the first edit, medians over repeated runs, enforcement AFTER generation rather than in the wording. Use when iterating on prompts or model-judged output.