agent-fleet-guardlisted

# agent-fleet-guard — guardrails for large agent orchestrations Dispatching one agent is routine. Dispatching **twenty** is a spend decision — and a fleet that half-dies silently poisons everything downstream. Six guardrails, all paid for with real incidents. **Threshold**: fan-out ≥ 20 subagents, **or** estimated ≥ 1M subagent tokens. Below that, just dispatch. ## ① Quote gate — quote first, wait for approval Before dispatch, run the estimator (same directory): ```bash ./fleet_estimate.sh --agents <N> --per <rough-tokens-per-agent> --json ``` Exit 10 = over threshold (`agents ≥ 20` **or** corrected estimate ≥ 1M) → **you must quote and wait**: > "Planning N agents, rough estimate X tokens, ×3 corrected ≈ Y tokens (**both are floors, not ceilings**) — the output is Z. Approve?" Give **both** numbers — the rough estimate and the ×3 correction. Why ×3: a real fleet quoted at ~0.9M tokens burned ~2.7M — roughly 3×, **and that was a lower bound**. Per-agent guesses run low; the estimator's default `--factor 3` bakes this in. ## ② Don't launch on an unstable connection If this session has recently seen `Connection closed` / connection-lost errors: **treat that as the signal, no probing needed** — crashed agents burn their tokens for nothing, and fail-closed pipelines then demand a full rerun. The classic failure is seeing scattered disconnects and *not counting them as a signal*. No existing signal but the fan-out is over threshold? Send **3 one-token probe agents** fir