improvelisted

# Gymnasium improvement proposal Self-improvement is the company's primary standing mission (ADR-0015), and it is **governed**: improvements are proposed → approved → implemented → measured. This skill produces the *proposal*; implementation only happens after an explicit Architect verdict. 1. **Gather evidence.** Improvement hunts start from records, not vibes: - `docs/PROGRESS.md` + past session reports (recurring blockers, split packages, 3-attempt failures); - `docs/DECISIONS-LOG.md` (clusters of minor decisions = a missing convention); - test flakiness / slowest suites; CI failures; `/doc-sync` drift history; - once the system runs: the Agora's `log.jsonl`, breaker trips, budget burn, memo rejection patterns, org metrics (SDD, Odeon artifacts). 2. **Pick ONE improvement** — the highest leverage-to-risk item. Not three. Scope it to ≤ 1 work package. 3. **Write the proposal** to `docs/gymnasium/proposals/GYM-<NNN>-<slug>.md` (next NNN from the directory; create it if missing) using exactly this structure: - **Evidence** — the observed friction, with refs (file, log line, report date). - **Proposal** — the change, concretely (files, mechanism, doc sections affected). - **Cost & risk** — effort, blast radius, what could regress. - **Success metric** — a number or binary check measurable within 2 weeks of landing (e.g. "median package completion needs ≤ 1 session", "zero drift findings in next /doc-sync"). No metric → not a