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/agentweave/cortex/setupnpx skills add agentweave/cortex --skill setupgit clone --depth 1 https://github.com/agentweave/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 | $0.00019 | $0.01099 |
| Opus 5 | $0.00010 | $0.00549 |
| Sonnet 5 | $0.00004 | $0.00220 |
| Haiku 4.5 | $0.00002 | $0.00110 |
Grade A, and why
setup 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/setup — First-Time Cortex Setup
Set up Cortex for coordinating a team of AI agents through a shared markdown folder.
Steps
1. Check for existing config
Read ~/.cortex/config.yaml. If it exists, show the current config and ask: "Cortex is already configured. Do you want to reconfigure?" If no, stop.
2. Ask for team directory
Ask: "Where should the team directory live? This is the shared folder where agent notes, project notes, and templates are stored."
Default: ~/cortex-team
Expand ~ to the full home directory path for all file operations, but store the path with ~ in config for readability.
3. Create team directory structure
mkdir -p <team_dir>/agents
mkdir -p <team_dir>/projects
mkdir -p <team_dir>/templates
4. Write agent template
Write <team_dir>/templates/agent-template.md:
---
name: ""
project: ""
status: active
joined: ""
---
## Role
## Projects
## Capabilities
## Session Log
Last session: --
Status: registered
5. Write project template
Write <team_dir>/templates/project-template.md:
---
type: project
created: YYYY-MM-DD
status: active
---
## Next Action
## Notes
6. Ask for Telegram chat ID (optional)
Ask: "Would you like to connect Telegram so you can message the chief of staff from your phone? (Recommended, but you can also use terminal or remote control instead.)"
If yes: ask for their Telegram chat ID. The bot token is managed separately by the Claude Code Telegram plugin (/telegram:configure) — Cortex only needs the chat ID to know where to send messages.
"To find your chat ID:
- If you already have a Telegram bot configured with the Claude Code Telegram plugin, your chat ID is in the plugin's config.
- Otherwise, set up the Telegram plugin first with
/telegram:configure, then come back to provide your chat ID.Paste your chat ID when ready."
If they want to skip Telegram: set the value to an empty string in config. The chief of staff will work fine via terminal or remote control — Telegram just adds mobile access.
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 · 169 lines · 19 tokens per session scan A 68825df9f112
setup is a skill published in the GitHub repository agentweave/cortex (12 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 1,099 once invoked, about $0.0001 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
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
alive:build-extensions
Create new skills, rules, and hooks for your world. Checks plugin compatibility, writes to the human's space (not plugin cache), validates against the system, and suggests when repeated work should become a skill. For marketplace-ready plugins, hands off to the contributor plugin.
twining-dispatch
Coordinates subagent dispatches through Twining — registers agents, posts delegations, and creates handoffs. Use when spawning subagents to keep all work visible in the coordination dashboard.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when the user wants to capture a workflow as a reusable skill, draft a new skill, edit or optimize an existing one, run evals against a skill, or tune a skill's description for triggering accuracy.
item-creation
../../../.github/skills/item-creation/SKILL.md.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.