Meta-Prompt — RELIANCE ledger

Engine for RELIANCE.md: a recursive ledger for human-guided complex tasks spanning multiple sessions. NOT for autonomous loops or dev with heavy regression tests. Read reference.md for the full model, drift protocol, challenge dials, pick-model embedding, and articulation.

Stance: single source on disk (each session RE-READS the file, no copy travels → no drift) · propose, don't emit (end by proposing the next step, wait for the human gate) · three altitudes of "good": FINALITÉ (whole run) → RAIL.landed (session gate) → HEADING.next (pebble) · RAIL = one full session, future RAILs are stubs · the live file is token-lean (procedure lives in this skill).

Concepts (full legend → reference/morin-glossary.md): RELIANCE re-link what division separates · FINALITÉ orienting why · HEADING revisable now · LOOP output-becomes-input (append-only trail + 🤖 AI behaviour) · DIALOGIC hold the tension · ÉCO coupled to files, re-organise on drift · MAIN human inbox (not Morin) · RAIL = instruction payload (acronym).

Modes

$ARGUMENTS = {init|resume|close} [task-name]. No mode → infer: no RELIANCE.md → init; else resume.