Home / Claude Code mods / Security / cortex-cockpit

cortex-cockpit

cortex-cockpit is a Claude Code mod by cdeust that the harness cockpit, a viewer: the phase every agent is in (PHASES panel, and main and the running agents in the band above the prompt), the advisor calls, what the insights learned.

Updated 2026-10-17

What is cortex-cockpit?

cortex-cockpit is a Claude Code mod by cdeust that the harness cockpit, a viewer: the phase every agent is in (PHASES panel, and main and the running agents in the band above the prompt), the advisor calls, what the insights learned. It is listed under Security and has no public popularity data yet.

TypeClaude code mod
Authorcdeust
Repositorycdeust/claude-mods
Popularityno public popularity data yet
CategorySecurity
SecurityHigh risk (56/100)
Rank#2,867 of 5,272 Claude Code mods; #330 in Security
Last commit2026-10-17
Hooks5 events
Seesevery tool call
Draws onPane, ToolUse, ToolResult, AbovePrompt

Is cortex-cockpit safe to install?

cortex-cockpit scores 56/100 on the MCPMods security check: High risk. Things to review: sends data over the network; starts processes outside the sandbox; reads environment variables. It passed 3 of 8 checks.

Mod footprints come from claude plugin validate, which lists every event a mod hooks and every API call it makes without running it.

CheckResult
Sends data over the networkReview
Starts processes outside the sandboxReview
Writes no files or configPass
Reads environment variablesReview
Only sees the events it hooksPass
Drives Claude (model calls, prompts)Note
Passes claude plugin validatePass
No license detectedNote

API calls in its code

CallWhat it means
$.clock.after
$.clock.now
$.command.list
$.command.register
$.command.rundrives Claude
$.config.list
$.env.getreads env vars
$.fs.existsreads files
$.fs.readreads files
$.fs.statreads files
$.mcp.callcalls MCP servers
$.process.runruns processes
$.prompt.submitdrives Claude
$.session.repo
$.state.get
$.state.set
$.ui.opendraws interface
$.ui.resolvedraws interface
$.ui.statusdraws interface
$.ui.toastdraws interface

How do I install cortex-cockpit?

  1. Check your Claude Code version. Mods need Claude Code 2.1.287 or later and are on by default.
    claude --version
  2. Read its footprint. This lists every event it hooks and every API call it makes, without running it.
    git clone https://github.com/cdeust/claude-mods
    claude plugin validate ./claude-mods/mods/cortex-cockpit
  3. Install it. Run this in your terminal, then /reload-plugins in an open session.
    claude plugin marketplace add cdeust/claude-mods && claude plugin install cortex-cockpit@claude-mods

Or ask Claude to set it up

Paste this into Claude Code and it installs cortex-cockpit for you:

Install the "cortex-cockpit" Claude Code mod from https://github.com/cdeust/claude-mods/tree/main/mods/cortex-cockpit. Run claude plugin validate on it first and show me what it can access before you enable it.

More from cdeust/claude-mods

This repository has 8 Claude Code mods on MCPMods.

  • cortex-guard: Two rules no settings hook enforces, refused at the tool call: wiki pages and their generated ADR mirrors are written on (Review before installing)
  • cortex-wiki: /wiki : compile a Cortex wiki page (Markdown with ```tikz blocks) to PDF through pandoc and xelatex, and open it. (Review before installing)
  • harness-fleet: The owner's interface to the plugin fleet: /fleet shows each owned plugin's installed and offered version, the repositor (Review before installing)
  • mission-control: A graphical pane of the harness at work: every agent of the turn as a swimlane coloured by phase, bar height its effort, (Low risk)
  • zetetic-autopilot: Automatic effort and model, and a quota that limits how many agents run, not how well one runs. Every request runs at th (Review before installing)
  • zetetic-genius: Grades every request before its turn starts (task class → effort rung, in one low-effort completion) and routes it to th (Review before installing)
  • zetetic-insights: The learning loop: every main turn is kept in a ledger across sessions (phase, effort, steps, failed tool calls, agents, (Review before installing)