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 commands/alphaaiservice/cortex/cortex-logingit clone --depth 1 https://github.com/alphaaiservice/cortexWhat 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 | $0.00028 | $0.00428 |
| Opus 5 | $0.00014 | $0.00214 |
| Sonnet 5 | $0.00006 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade B, and why
cortex-login scanned grade B 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 yesterday.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
`~/.cortex/credentials.json` with `chmod 600`. What it actually says
/cortex-login — Connect to Cortex Cloud
Logs this machine into Cortex Cloud using the OAuth 2.0 Device Authorization
Grant (RFC 8628) — the same "open a URL, type a code" flow as gh auth login or
aws sso. No password is ever typed in the terminal.
$ARGUMENTS (optional) overrides the Cortex Cloud base URL (default
https://cloud.cortex.alphaai.com). You can also set CORTEX_CLOUD_URL.
What happens
- The plugin calls
POST /auth/deviceand shows you a short user code and a verification URL (…/activate). - You open that URL in your browser, sign in to the dashboard, and enter the code.
- The plugin polls
POST /auth/token(honoring the server'sintervalandslow_down) until you approve, then writes the device token to~/.cortex/credentials.jsonwithchmod 600.
The raw token only ever lives on your disk — Cortex Cloud stores just its sha256 hash. Telemetry and premium features stay off until you connect; nothing here is required to use the plugin locally.
Run it
Execute the device-grant flow (this will print a code and wait for approval):
bash "${CLAUDE_PLUGIN_ROOT}/scripts/cortex-login.sh" $ARGUMENTS
When it prints the code, tell the user — clearly — to open the verification URL and
enter the user code, then wait. On success report that the machine is connected; on
timeout or an expired/denied code, tell them to run /cortex-login again. Use
/cortex-status to check the connection later and /cortex-logout to disconnect.
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.
- yesterday First seen · 39 lines · 28 tokens per session scan B fd6f52345332
cortex-login is a command published in the GitHub repository alphaaiservice/cortex (1 stars, last pushed 25d ago), licensed MIT. It adds 28 tokens to every session and 428 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
e2e
使用 Playwright 对 Web UI 进行端到端测试（支持视频录制、Trace 录制、控制台/网络日志捕获）.
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
review
Compare a reference design against an implementation. Accepts Figma URL, image file, or browser URL as reference.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.