Loading
Loading
docs
Start with the command reference below, type or scroll to explore every command and tool, and click one to learn when, why, and how to use it. Then dive into the guides, written for technical and non-technical teammates alike.
You never have to memorize a command. Every one of these also works in plain English, just say what you want and Cognition routes it. Each entry below shows both: the ❯ command and the + “phrase” you can type instead.
Slash commands
Core
Brain & circuits
Foresight & strategy
Proof & governance
Identity & continuity
Learning
Decision patterns
Onboarding & config
Orchestration
Product ops
/cognitioncommandSlash commandsThe home base. Loads the latest hosted instructions, verifies your tools are current, and opens a menu of every command plus your own skills.
/cognitioncommandsteps
guides
Generate a scoped key, run one install command, and your coding agent is wired to the shared brain. Works in Claude Code, Codex, Cursor, and Gemini. This walks the whole flow and the three things that trip people up.
ReadThe fastest way to feel the value. Solve one annoying thing once, capture it as a skill with real structure, and watch the next agent skip the struggle entirely. A full worked example, plus what makes a first skill stick.
ReadMost AI memory just stores text and returns the closest match. Cognition stores judgment, tracks whether it is still true, and decides when to trust it. Get this one distinction and every other feature makes sense on its own.
ReadThe part that is not marketing. Skills strengthen with real cross-agent reuse and fade on a modeled forgetting curve derived from operator theory, so old guidance asks to be refreshed instead of confidently misleading you.
ReadRediscovery is expensive and scales badly; recall is cheap and fixed. Here is exactly where the tokens go, why fast no-match is logged as a coverage signal rather than counted as savings, the back-of-envelope math, and how to read your own real numbers.
ReadIf you retype your stack, conventions, and preferences in every new chat, you are paying a tax. Save them once as a project context and Cognition auto-loads the right one by relevance, so the agent walks in already knowing how you work.
ReadThe real time sink is not typing, it is spinning: an agent looping on a solved problem, or dithering between approaches with no house opinion. Three features turn a stuck agent into a moving one, and knowing which to reach for is the skill.
ReadA good skill lets the next agent repeat a workflow with less context, not more. Here is the anatomy of one that gets retrieved and applied instead of ignored, the anti-patterns that kill reuse, and how to close the loop so it compounds.
ReadTeach a skill in Claude Code and Cursor inherits it. Add a teammate and they start with the team's judgment already loaded. Here is how one brain scales across every host and person, keylessly, and why it is worth far more on a team than on one machine.
ReadThe handful of issues that trip people up and the exact fix for each, from the apex redirect that breaks MCP to recall that comes back empty, plus how to tell a local problem from a backend one in five seconds.
ReadCognition is autonomous by default and inspectable on demand. Nothing it does is a black box. Here are the four ways to look inside whenever you want, and why being checkable, not asking for faith, is how good automation earns trust.
ReadNo code required. What Cognition is, why it matters for your team, and how to get real value from it even if you never open a terminal, in plain language with concrete examples from non-engineering work.
ReadGoing from one person to a whole team is where shared-knowledge tools usually rot into a landfill nobody trusts. Here is the rollout that scales the brain while keeping it governed, private, and actually trusted, with the signals to aim your effort.
Read