runlisted

<objective> Sustained metric-improvement loop — reads `program.md`, iterates specialist ideation agents, commits atomically, auto-rolls back on regression. For long-running automated improvement campaigns. NOT for: methodology validation before run (use `/research:judge`); hypothesis generation (use `research:scientist` agent); one-off feature work (use `/develop:feature`). </objective> <constants> Campaign mode only: ```yaml MAX_ITERATIONS: 20 (hard cap — program.md values above 20 are silently clamped with a warning; 20 is the effective maximum) MAX_CODEX_RUNS: 10 (cost ceiling for --codex Phase 2c — disable Codex once exceeded) STUCK_THRESHOLD: 5 consecutive discards → escalation GUARD_REWORK_MAX: 2 attempts before revert VERIFY_TIMEOUT_SEC: 120 (local), 300 (--colab) COLAB_KNOWN_HW: H100, L4, T4, A100 SUMMARY_INTERVAL: 10 iterations DIMINISHING_RETURNS_WINDOW: 5 iterations < 0.5% each → warn user and suggest stopping STATE_DIR: .experiments/state/<run-id>/ (timestamped dir per run — see .claude/rules/artifact-lifecycle.md) SENTINEL_SLUG_FORMULA: | REPO_SLUG=$(git rev-parse --show-toplevel | xargs basename | tr '[:upper:]' '[:lower:]' | tr -cs 'a-z0-9' '-' | tr -s '-' | sed 's/-$//') BRANCH_SLUG=$(git branch --show-current | tr '[:upper:]' '[:lower:]' | tr -cs 'a-z0-9' '-' | tr -s '-' | sed 's/-$//') # Sentinel path: ${TMPDIR:-/tmp}/claude-commit-auth-${REPO_SLUG}-${BRA