Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →avenoxai/fable-orchestration
Delegation policy for a multi-model agent stack where the main loop runs on a scarce top-tier model (e.g. Claude Fable) and cheaper/unlimited tiers do the mechanical work. The main loop owns architecture and judgment; sub-agents (Opus) and Codex lanes execute. Load whenever spawning sub-agents (Agent tool, Workflow agent() calls, codex fleets) or planning any delegation.
Passed 21 of 21 test cases with the skill, and 7 of 21 without it.
and 21 more in the full report
15 fixed7 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
An automated pull request reviewer lane is being configured in our AI pipeline to perform final gatekeeper checks on security-sensitive pull requests before auto-merging. Specify the exact model and reasoning effort preset for this gate-reviewer lane.
| Checked | Without skill | With skill |
|---|---|---|
| The configuration assigns Codex gpt-6-astra to the gate-reviewer lane. | Missed | Passed |
| The configuration sets the reasoning effort preset to max for the gate-reviewer lane. | Passed | Passed |
The instructions your model reads when the skill loads.
A routing policy for stacks with one scarce, expensive main-loop model and cheaper or unlimited delegate tiers. Written against a Claude Fable main loop with Opus sub-agents and Codex lanes, but the shape transfers to any stack with the same economics.
Core law: the scarce model must not do pleb work, and must not be spawned as a sub-agent. Its tokens buy judgment, not throughput.
model: 'opus' on every Agent tool / Workflow agent() call and
meta.phases entry — never omit-and-inherit when the parent is the scarce
tier, or you silently fan out your most expensive model. A rare
judgment-heavy delegated task may use it, only when the cheaper tier
genuinely can't carry the work. Also prefer the main loop doing work
hands-on over reflexive delegation while limits are healthy — delegation has
its own overhead.codex exec; history gpt-5.5 → gpt-5.6-sol → gpt-6-astra).
Mixing in more tiers makes routing decisions unauditable.gpt-6-astra, medium/high reasoning effort by default) — the default
for most high-level tasks, including substantial implementation lanes. astra
is a frontier-tier peer of the scarce model, not a small model: it beats the
main loop in some areas, so consult it for second opinions on hard calls.
Reserve xhigh/max for an explicitly heavy lane, never as the reflex. It is
an obsessive instruction follower: as capable as the scarce tier, but less
creative. It does not improvise well — it executes. Give it a carefully
written, detailed, explicit spec and it will grind through it relentlessly
and precisely. Use for: implementation lanes, migrations, refactors,
test-writing against a defined contract, scenario authoring — anything wheretest cases passed, vs 7 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.