← ClaudeAtlas

firstpasslisted

Use BEFORE any multi-agent fan-out, swarm, or Workflow orchestration — and when assigning a model tier to any delegated unit of work. Confidence-gated model routing: rubric-based base-tier assignment (cheap→standard→frontier→apex), objective escalation triggers (verification failure, disagreement, uncertainty flags), hysteresis rules, and the structured handoff payload that lets higher tiers resolve only the residue lower tiers couldn't. Triggers on "fan out", "swarm", "parallel agents", "which model", "assign tiers", "dispatch", "model routing", "token cost".
undercutsh/firstpass · ★ 1 · AI & Automation · score 67
Install: claude install-skill undercutsh/firstpass
# Tiered Dispatch — confidence-gated model routing Goal: every unit of work runs at the cheapest tier that can pass verification, and escalation is driven by **objective signals** (failed checks, disagreement, explicit uncertainty flags) — never by asking a model how confident it feels. LLM self-reported confidence is poorly calibrated; this skill treats it as a routing hint only, never as approval. This skill defines the ladder logic and is model-agnostic. It uses four generic tier names — **cheap**, **standard**, **frontier**, and an optional **apex** — instead of any vendor's specific model names. Resolve tier names to actual model IDs for your agent (Claude Code, Codex, Cursor, or other) via `models.md` in this same directory. ## Scope: this rubric tiers execution, not judgment A single request usually mixes two kinds of work: deciding what to build and which tradeoffs matter (judgment), and then building it against that decision (execution). This entire skill — the six-flag rubric, the escalation triggers, the residue-only handoff — applies to the **execution** half. It has no validated answer for the judgment half; treat planning/strategy calls as frontier-tier by default until that's tested (see "Anti-patterns" and the site's Honest limits, #05). Don't let "but the whole session touched a frontier model at some point" become an excuse to skip tiering the execution units that make up most of the token volume. ## The two routing decisions 1. **Planning tier** — who