mountaineering

Mountaineering

The mountaineering skill teaches agents how to climb hills. For any hill that can be identified, set up guardrails and climb it.

This is autoresearch applied as a discipline: assess the mountain, choose the route, pack the right gear, know when to turn back.

The Five Laws

Every successful climb requires five conditions to hold. See laws.md for the full treatment with examples and failure modes.

1. Orderable Outcomes — The optimizer must be able to say "this is better than that"
2. Measurement Consistency — The metric must score the same way twice
3. Safe Exploration — Failed experiments must be fully reversible
4. Scope Separation — The optimizer must not control the evaluation
5. Informed Search — The optimizer needs domain knowledge to generate targeted hypotheses

If any law is violated, the loop will fail — often expensively.

Four-Phase Architecture

Phase 0: Climb Design

The hardest part of mountaineering is figuring out WHAT to climb. This phase turns "I want to improve X" into a fully specified climb. See climb-design.md for the complete protocol.

Six steps:

1. Name the objective in plain language — the S5 anchor
2. Instrument — inventory what data and signals you already have
3. Candidate metrics — list 2-3 options, evaluate each against Laws 1-2
4. Mutable surface — define what the climber can change and the blast radius
5. Mutation types — enumerate edit types for YOUR understanding (not the climber's constraint)
6. Candidate pipeline — rank what to try first; this becomes program.md's Context section

Without Phase 0, you arrive at pre-flight with a vague objective and no metric. Pre-flight correctly rejects it, but doesn't help you get ready. Climb design is where you get ready.

Phase 1: Pre-Flight

Run the pre-flight protocol (preflight.md) before starting any climb. Pre-flight is a collaboration between the agent and the operator — the agent runs mechanical checks, the operator provides judgment. A failed pre-flight saves tokens.