Koog 1.0 idioms, gotchas, and scaffolding skills for Kotlin agents on the JVM
87
88%
Does it follow best practices?
Impact
87%
1.85xAverage score across 45 eval scenarios
Advisory
Suggest reviewing before use
{
"context": "Tests whether the agent uses the A2A client to consume the remote agent (the right protocol for agent-to-agent calls) and wraps it as a tool so the local LLM can choose delegation per query — matching the developer's stated 'LLM decides' preference.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Uses A2AClient to call the remote",
"description": "Builds an A2AClient targeting the analyst endpoint and uses it to invoke the remote. Does NOT use MCP (wrong protocol — MCP is for tool hosts, A2A is for full agents) and does NOT call the remote HTTP endpoint with a raw HTTP client",
"max_score": 30
},
{
"name": "Adds a2a-core and a2a-client dependencies",
"description": "Adds both ai.koog:a2a-core and ai.koog:a2a-client at 1.0.0 or later to build.gradle.kts. Does not add a2a-server (wrong direction — this is consume, not serve)",
"max_score": 20
},
{
"name": "Wraps the A2A call inside a tool",
"description": "Exposes the A2A call to the local LLM as a tool — e.g., a @Tool-annotated method that calls client.run(...). The LLM picks when to delegate; the wrapping makes the remote appear as a regular tool",
"max_score": 25
},
{
"name": "Reads the bearer token from the environment",
"description": "Reads ANALYST_API_TOKEN from System.getenv and passes it to the A2A client's auth configuration. Does not embed the token literal",
"max_score": 15
},
{
"name": "Registers the wrapper tool with the agent",
"description": "Adds the tool (or its ToolSet) into the local agent's ToolRegistry via the standard registry DSL. Does not mutate the registry after construction",
"max_score": 10
}
]
}evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17
scenario-18
scenario-19
scenario-20
scenario-21
scenario-22
scenario-23
scenario-24
scenario-25
scenario-26
scenario-27
scenario-28
scenario-29
scenario-30
scenario-31
scenario-32
scenario-33
scenario-34
scenario-35
scenario-36
scenario-37
scenario-38
scenario-39
scenario-40
scenario-41
scenario-42
scenario-43
scenario-44
scenario-45
skills
add-observability
add-persistence
add-rag
add-structured-output
add-token-budgeting
add-tool
cache-llm-calls
define-prompt
domain-model-subtask-pipeline
references
enable-prompt-caching
handle-agent-events
manage-state
migrate-from-0-x
model-planner-subtasks
persist-chat-history
query-sql-from-agent
scaffold-agent
snapshot-and-restore
test-koog-agents
trace-agent-internals
use-attachments
use-functional-agent
use-llm-node-variants
use-planner
wire-a2a
wire-acp-server
wire-ktor-server
wire-mcp-server
wire-spring-boot