Plugin

co-dialectic

Co-Dialectic is a real-time prompt coaching system that activates automatically on every response. It shows a persistent status line tracking your current AI persona, prompt quality, and context window health. When your prompt could be sharper, it suggests an improved version and explains why in one sentence — then waits for your choice. Over days, it tracks your prompt quality percentage (users typically progress from 45% to 91% clear prompts in 10 days). It auto-detects the right expert persona for each question, teaches you prompting techniques by naming them when you use them naturally, and generates context handoff summaries before your conversation degrades. Works as a learning flywheel: you correct the AI, it captures the lesson as a generative principle, applies it going forward, and both sides get sharper. Five protocols, zero configuration — just say "cod" to activate.

• Published source
• Repository

Analysed

11 October 2026

Last observed

12 October 2026

What the code does

• Runs shell commands Code that starts system commands on the machine it runs on.
• Starts other processes Code that launches separate programs.
• Sends data to outside servers Code that posts data to network addresses.
• Runs hooks automatically Hooks that execute without being called explicitly.
• Runs an AI coding agent unsupervised Code that starts an AI coding agent with its approval prompts switched off.
• Reads AI and developer logins Code that refers to AI tool credentials or publishing tokens, such as .npmrc.

Having a capability is not wrongdoing; many tools need these to do their job. It tells you what to check before you install.

This is public metadata, not a safety certification or complete assessment. Static analysis cannot establish what a tool does at runtime.