From myco
Boots Myco substrate health check at session start: returns boot brief, active reflexes, and raw-notes backlog. Invoke manually when SessionStart hook did not run or substrate state may have drifted.
How this skill is triggered — by the user, by Claude, or both
Slash command
/myco:hungerThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Myco's boot ritual, per L1 rule R1. Every session begins here.
Myco's boot ritual, per L1 rule R1. Every session begins here.
python -m myco --json --project-dir "$CLAUDE_PROJECT_DIR" hunger
If $CLAUDE_PROJECT_DIR is not set (you are invoking outside Claude
Code), substitute the substrate root path, e.g. "$PWD".
JSON with at least:
boot_brief — path to the newly written brief under .myco_state/.reflexes — HIGH-severity signals that gate all other work until
addressed. Read these first.backlog — raw-notes count, stale-reflection flags, MB1 / MB2
indicators.reflexes first. Any HIGH item is addressed before the user's
request./myco:sense (or myco sense) before
any factual claim about the substrate./myco:session-end: the matched ritual at session close (the
skill is kept under its legacy directory name; the canonical verb
is myco senesce, with --quick for SessionEnd hooks).brief) is exposed as MCP tools when the plugin's MCP server is
running.npx claudepluginhub battam1111/myco --plugin mycoManages a Myco cognitive substrate (a project directory with _canon.yaml and MYCO.md) for agent-first, long-term knowledge across sessions. Provides 20 fungal verbs for ingestion, digestion, circulation, and homeostasis.
Shows freshness of health data sources (Apple Health, Oura, Fitbit, labs), last coach prescription and completion, missed-day count, lab status flags, and auto-trigger hook installation status for debugging the health-mcp auto-trigger chain.