helios

Helios Behavioral Science

Helios observes your behavioral patterns and helps your agent learn your preferences. It detects when behavior drifts from your declared profile and proposes negotiated updates.

Commands

Route based on $ARGUMENTS:

• /helios init [persona] — bootstrap Helios and onboard from ~/.claude/CLAUDE.md and the active output style
• /helios or /helios status — show current behavioral profile
• /helios drift — check for behavioral drift
• /helios negotiate — review and accept/reject proposed changes
• /helios import <path> — import a personality file into Helios
• /helios export [format] — export behavioral profile (yaml, json, soulspec)

Init

When the user runs /helios init, or asks to (re)onboard from ~/.claude/CLAUDE.md: run the CLI directly. There's no MCP tool for this — it also sets the default persona, a filesystem-level change no MCP tool exposes.

helios-mcp init [persona]

Omit [persona] to reuse the already-configured default, or developer on a fresh install. Imports ~/.claude/CLAUDE.md and the active output style into that persona's user level as the authoritative source and makes it the default persona. Idempotent — rerunning overwrites the persona's user-level profile instead of duplicating it.

Session Start

!helios-mcp status 2>/dev/null || echo "Helios not yet bootstrapped"

At the beginning of each session, call get_behavioral_context to load the user's behavioral preferences. Apply these preferences to guide your communication style, epistemic approach, interaction patterns, and risk posture. Omit persona_name unless the user names a specific persona — it falls back to HELIOS_DIR/default_persona, then "default". Pass model with your own model id when you know it (it's usually stated in your system prompt, e.g. claude-sonnet-5) so the context can counter that specific model's observed tendencies rather than the average across models.

Tool: get_behavioral_context
Args: { "model": "<your model id, if known>" }