simplicio-loop

Unified public entrypoint for Simplicio's body-of-work orchestration: core + loop in one command. Use when the user types /simplicio-loop, says "ralph loop", "keep iterating until done", "finish all open issues", or asks to drain a queue of work autonomously. Runtime-agnostic: binds a real stop-hook where the host supports hooks (Claude, Cursor); otherwise self-paces via the host scheduler. The older /simplicio-tasks surface is a legacy alias; never escape the loop with a false promise.

Legacy compatibility alias for `/simplicio-loop`. Use only when an older install, adapter, or saved prompt still invokes `/simplicio-tasks`; immediately route the run through `.claude/skills/simplicio-loop/SKILL.md`, which now owns the public core + loop protocol.

Evolutionary optimize-by-metric loop — mutate a target, evaluate against fixed criteria, KEEP if the score improves (commit) or REVERT if it doesn't (git checkout), repeat, plateau-break after N stagnated runs. Adapts Karpathy's `autoresearch` pattern (and the ECC `autoresearch-agent`) with mandatory yool guardrails (§11 caps), git-isolated branch discipline, an anti-Goodhart eval order (correctness gate FIRST, score SECOND, labeled tokenizer), a local-first mutation ladder, and a `simplicio.savings-event/v1` receipt per run. Use when the user says "optimize this by <metric>", "autoresearch loop", "evolutionary optimize", "mutate/eval/keep-revert", or asks to shrink tokens/latency/bundle size/improve pass-rate against a fixed, measurable eval. Worker: `scripts/autoresearch.py`.

Terminal-first execution — answer facts with the shell, never with the LLM. Use whenever a step needs a fact about the filesystem, git, processes, or system resources, or runs a build/test/lint/diff whose output would flood context. Substitutes deterministic shell/CLI calls for native LLM operations and clamps their output 60–90% (rtk-style) with a failure-safe tee cache, signatures-only reads, and an optional auto-rewrite hook. This is the token-economy spine of simplicio-tasks, usable standalone.

Deep, adversarial branch review — parallel subagents on separate rubrics (security/correctness, code-quality, and does-it-reproduce), spawned in one message, then deduped into one verdict. Runs for EVERY item, no TRIVIAL/SMALL shortcut — it is 3 of the 6 roles in simplicio-tasks' minimum-agent floor. Use before merging any work, when the user says "review this branch/PR hard", "thermo-nuclear review", "is this safe to merge", or when simplicio-tasks needs the Step 4c adversarial verify gate. Scopes strictly to the diff; refutes rather than rubber-stamps.

Persist what a run taught you so the next run is cheaper and more correct — mine high-signal lessons from the trajectory, dedup them, and write them back to AGENTS.md / memory so they're applied not re-derived. Use after a run or at session end, when the user says "remember this", "do a retrospective", "learn from this run", or when simplicio-tasks closes its self-audit. Keeps memory lean: durable, reusable bullets only — no transcripts, no one-offs.

Cut output and memory tokens without losing meaning — terse prose levels (caveman-style) that preserve code/paths/URLs byte-for-byte, plus a one-time memory/doc compaction pass that pays back every future turn. Use when replies or worker reports are verbose, when standing context (CLAUDE.md/AGENTS.md/notes) is bloated, or when simplicio-tasks needs its output-side + input-side token discipline. Compression NEVER touches code, identifiers, or a safety confirmation.