The agent loop
When an agent receives a task, it follows this flow:Discovery
Skills are discovered through the filesystem. An agent knows about skills in its configured skill directories. When a task arrives, the agent scans skill descriptions to find relevant ones.Execution
When a skill includes executable scripts, the agent runs them as child processes:Environment variables
Skills can receive configuration through environment variables. This keeps secrets out of command-line arguments (which appear in process listings).Exit codes
0— success, stdout contains the result- Non-zero — failure, stderr contains the error message
Composition
Skills can reference other skills. A “deploy” skill might call a “git” skill and a “docker” skill internally. This is just scripts calling scripts — no orchestration framework needed.What SCP does NOT define
SCP intentionally avoids specifying:- Transport protocols — there is no transport; skills are local files
- Authentication handshakes — use environment variables or config files
- Capability negotiation — the agent reads markdown; it understands what it reads
- Lifecycle management — no connections to open or close
- Streaming protocols — stdout is already a stream