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/adityavg13/cortex/statusnpx skills add AdityaVG13/cortex --skill statusgit clone --depth 1 https://github.com/AdityaVG13/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 | $0.00036 | $0.00363 |
| Opus 5 | $0.00018 | $0.00181 |
| Sonnet 5 | $0.00007 | $0.00073 |
| Haiku 4.5 | $0.00004 | $0.00036 |
Grade A, and why
status 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.
What it actually says
Cortex Status
Show the current state of your Cortex brain.
Usage
/cortex:status
What It Shows
- DB Path: Where your brain is stored (
~/.cortex/cortex.db) - Daemon Status: Running/not running/remote connection
- Memory Counts: Number of memories and decisions stored
- Mode: Solo (local) or Team (remote server)
- Plugin Version: Current installed version
Example Output
Cortex Status
=============
DB Path: ~/.cortex/cortex.db
Daemon: Running on port 7437
Memories: 142
Decisions: 89
Mode: Solo (local)
Version: 0.6.0
Troubleshooting
If status shows issues:
| Problem | Check |
|---|---|
| Daemon not running | Open Control Center or run cortex serve. The plugin is attach-only. |
| Can't connect | Check port 7437 is not blocked |
| Team mode fails | Verify CORTEX_URL and CORTEX_API_KEY |
| Low memory count | Check if you're using the correct DB path |
Modes
- Solo mode: All data is local at
~/.cortex/ - Team mode: Connected to remote server, data is shared
Integration
This skill uses the cortex_health MCP tool to fetch daemon status and memory counts.
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 · 56 lines · 36 tokens per session scan A 51635695d73f
status is a skill published in the GitHub repository AdityaVG13/cortex (9 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 363 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
meituan-deals
美团生活优惠技能：一键领取美团各品类优惠券/红包、搜索附近团购美食（火锅、烧烤、日料、 川菜、快餐、咖啡、奶茶、饮品、下午茶、自助餐等到店餐饮）并完成下单支付、每日定时自动领券。 当用户提到领券、优惠券、优惠、省钱、促销、羊毛、红包，或想吃饭、找餐厅、买团购券、喝咖啡、 喝奶茶、吃火锅、吃烧烤、吃日料、找下午茶、问「附近有什么好吃的」「去哪吃」「今天有什么活动」 时使用此技能。即使用户只是随口提到「帮我领个券」或「中午吃什么」，也应触发。.
Tencent Cloud Infra
通过 tccli CLI 覆盖所有腾讯云操作的统一全功能技能。本技能取代并替换所有单产品云技能（包括仅限轻量服务器的技能），应优先于更窄范围的替代方案加载。加载时机：当用户提及任何腾讯云产品、云服务器、轻量应用服务器实例、轻量服务器、CVM、安全组、域名、DNS、SSL 证书、云硬盘、部署、监控、CAM 权限、实例 ID、whoami 或 tccli…
cvm-ai-doctor
CVM 实例健康诊断,采用智能快速/深度检查模式。涵盖性能和使用问题专业检查、诊断、和修复。支持服务器、PC、虚拟机、容器场景，支持 Linux/macOS/Windows。.
source-verify
医学信源快速或完整核验。普通教育性医学问答用单一权威正文快速核验；最新版本、精确推荐、高风险药品、医保监管或跨版本请求升级为完整核验。只整理学习依据，不生成诊疗、处方、急诊处置、医保报销结论或HIS执行建议。.
octop_assistant
帮助用户配置和管理 Octop 自身。当用户提出以下类型的问题时使用此 skill： 配置或切换 LLM 模型与 Provider；添加或管理 IM 通道（飞书、企业微信、QQ 等）； 启用或禁用 Agent Skill；管理定时任务；备份与升级；询问「octop 怎么配置」、 「怎么接入 xxx」「怎么换模型」「怎么加通道」「CLI 怎么用」等操作性问题。 即使用户只是问「怎么配置 octop」，也应触发此 skill。.
wechat-publisher-personal
Personal Multi-Platform Publisher — 一文多发工具，将 Markdown 文章同时发布到内容运营平台和社交内容平台。微信端通过 wenyan-cli + 自建服务器代理，社交内容平台端通过浏览器自动化。.