Unverified50% confidenceSolutionExact time
The complete execution chain of a general-purpose agent is: select model → load skills → map sandbox → stream execution → tool call → LLM processing → return result → close sandbox.
1
Sources
50%
Confidence
Long-term
Relevance
9/29/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe mainstream skill package execution method is to load skill instructions into the agent's context window, relying on the agent itself to understand and follow these instructions.78% similarUnverifiedIn a layered agent architecture, the top-level orchestration agent is responsible for decision-making and uses a powerful model, while the bottom-level execution agents handle repetitive work using mid-tier models.77% similarVerifiedThe core architecture of an agent can be summarized as: Agent = Large Language Model (LLM) + Tools + Memory + Task Scheduling.76% similarUnverifiedThe core methodology of the guide is to standardize repetitive work with Skills, connect automation pipelines with Hooks, and decompose complex tasks with Plan mode.76% similarUnverifiedThe Skill mechanism uses on-demand loading: it first sends the metadata of all Skills to the large model, and after the large model selects the matching Skill, the full instructions are loaded.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/958226API
curl https://kongchang.com/api/v1/knowledge/claims/958226MCP
get_claim(id=958226)