From 590db2f488c7c7b9698dbb1d3c8f7b0e605b7ed9 Mon Sep 17 00:00:00 2001 From: Bernardo Magri Date: Sat, 18 Jul 2026 09:04:17 +0100 Subject: [PATCH] docs(agent): require frontier-led delegation workflow Make bounded lower-cost implementation delegation the default for feature work, while keeping architecture, integration, review, and final verification with the frontier lead. Require explicit disclosure when cheaper-model selection is unavailable and prohibit presenting generic agents as Luna. --- AGENTS.md | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/AGENTS.md b/AGENTS.md index aeec80c..dc8da85 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -10,6 +10,20 @@ creates the implementation plan, decomposes work, assigns non-overlapping file ownership, reviews every delivered change, integrates the result, and performs the final verification. +This lead/delegate/review sequence is the required default for feature work, +not an optional optimization. Before writing feature implementation, the lead +must identify bounded coding slices and dispatch them to cheaper coding agents +(for example Luna) whenever the orchestration environment exposes those models. +The frontier lead should normally restrict its own edits to shared contracts, +cross-cutting or data-loss-sensitive logic, integration fixes, and work that is +too tightly coupled to delegate safely. + +If agent spawning is available but cheaper-model selection is not exposed, the +lead must say so explicitly before implementation. It must not imply that a +generic spawned agent is Luna or otherwise cheaper. In that environment the +lead may use available agents for bounded parallel work, but should explain the +limitation and still retain the same ownership, review, and verification duties. + Delegate bounded coding tasks to cheaper/lower-cost agents whenever the orchestration environment supports model selection. Coding agents should implement clearly specified slices; they should not independently redefine the