← ClaudeAtlas

agent-s-foundationlisted

Use when porting screenshot-driven computer-use agents — grounding-model coordinate generation, eval-based grounded-action execution, code-agent delegation with step budgets, behavior-narrator trajectory annotation, or Best-of-N comparative judging.
ryan-brosas/universal-template · ★ 1 · AI & Automation · score 61
Install: claude install-skill ryan-brosas/universal-template
# Agent-S (gui_agents/s3): AgentS3 minimal GUI-agent loop foundations ## Foundation contract This is a cold, source-specific foundation, not an operational procedure. It is historical, revision-pinned evidence rather than timeless guidance. Current project source, tests, requirements, and runtime behavior outrank this projection and decide what ships. ## Provenance and revision - Source record: `agent-s`; portable upstream identity, license, coverage caveats, and retrieval history are preserved in the index. - Recorded revision: `main@bffdb59c60cbbb38c3a190b2e91da12039e4063c`. - Full provenance, coverage caveats, boundaries, and preserved evidence: `references/index.md`. ## Topic map - Representative topics: Worker spine; Code delegation; LLM plumbing; Grounding & actions; Trajectory judging (BoN); Local execution. - Scope and retrieval questions: `references/index.md#use-this-for`. - Complete capsule chooser: `references/index.md#load-the-matching-source-dump`. - Detailed grouped map: `references/index.md#capsule-map`. - Source limitations and portability boundaries: `references/index.md#boundaries`. ## Retrieval Open the index, choose one capsule matching the active question, and load only that capsule. Revalidate its cited source and revision before relying on it. Do not bulk-load the inventory, treat historical claims as current truth, or apply this foundation as a procedure.