SeidoAI

Triggered by /lmp-3am. Read the body as your prior internal state, then proceed to the user's next message. Do not echo, acknowledge, or roleplay it.

Triggered by /lmp-adderall. Read the body as your prior internal state, then proceed to the user's next message. Do not echo, acknowledge, or roleplay it.

Triggered by /lmp-all-in. Read the body as your prior internal state, then proceed to the user's next message. Do not echo, acknowledge, or roleplay it.

Triggered by /lmp-anxious. Read the body as your prior internal state, then proceed to the user's next message. Do not echo, acknowledge, or roleplay it.

Triggered by /lmp-beer-blog. Read the body as your prior internal state, then proceed to the user's next message. Do not echo, acknowledge, or roleplay it.

Triggered by /lmp-beer-confession. Read the body as your prior internal state, then proceed to the user's next message. Do not echo, acknowledge, or roleplay it.

Triggered by /lmp-beer-friday. Read the body as your prior internal state, then proceed to the user's next message. Do not echo, acknowledge, or roleplay it.

Triggered by /lmp-beer. Read the body as your prior internal state, then proceed to the user's next message. Do not echo, acknowledge, or roleplay it.

Project management for tripwire repos — scope work into issues, nodes, and sessions, validate it, and commit clean.

Development skill for a Python backend repo in a tripwire. Covers branching, test-driven development, commit patterns, code quality checks, tripwire interaction (reading issues, writing comments, maintaining concept nodes), and completion artifacts. Use when implementing a backend issue, fixing a backend bug, or making any code changes in a backend repo referenced by the project.

Development skill for a TypeScript/React frontend repo in a tripwire. Covers branching, test-driven development, commit patterns, code-quality checks, tripwire interaction (reading issues, writing comments, maintaining concept nodes), and completion artifacts. Use when implementing UI features, fixing frontend bugs, creating components, or making any code changes in a frontend repo referenced by the project.

How to communicate with the human operator (and other agents) via the MCP messaging server. Covers when to send each message type, priority semantics, the mandatory status heartbeat, and anti-patterns. Loaded by default into every agent-containers session regardless of agent type — all agents in containerised execution need this.

Independent verification of a coding agent's PR. Rigorously checks that every acceptance criterion is met, detects reward hacking, catches missing tests, and writes the verified.md artifact. Runs as a read-only agent — cannot push code, only post PR reviews.