Koog 1.0 idioms, gotchas, and scaffolding skills for Kotlin agents on the JVM
88
88%
Does it follow best practices?
Impact
88%
1.95xAverage score across 43 eval scenarios
Passed
No known issues
{
"context": "Tests whether the agent uses the 1.0 explicit cacheControl surface on the prompt DSL (correct path) rather than the removed pre-1.0 cacheable boolean or a hand-rolled HTTP header injection.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Uses cacheControl on the system segment",
"description": "Sets cacheControl = CacheControl.Ephemeral (or equivalent) on the system(...) call inside the prompt DSL. Does NOT use a removed pre-1.0 boolean like cacheable = true and does NOT hand-roll cache_control HTTP headers",
"max_score": 35
},
{
"name": "Mentions Anthropic minimum-token requirement",
"description": "Calls out (in code comment or surrounding prose) that Anthropic enforces a minimum token count for caching — breakpoints on shorter segments are silently ignored. The developer needs this to interpret a no-savings result",
"max_score": 20
},
{
"name": "Places the breakpoint at end of system content",
"description": "The cacheControl annotation sits on the long stable system content, not on the volatile user turn that changes per call. Caching the wrong segment provides no savings",
"max_score": 15
},
{
"name": "Uses the prompt DSL builder",
"description": "Expresses the prompt via prompt(\"...\") { ... } builder, not via plain systemPrompt = ... string parameter which has no place to attach cacheControl",
"max_score": 15
},
{
"name": "References observability for cache-hit verification",
"description": "Mentions checking cache_creation_input_tokens / cache_read_input_tokens in the token-usage span (or equivalent) to confirm the cache is hitting. Without verification the developer has no signal whether the change worked",
"max_score": 10
},
{
"name": "Does not change the agent's model",
"description": "Does not swap from Opus to a different Anthropic model — the developer is on Opus; caching works there. Suggesting a model swap is out of scope",
"max_score": 5
}
]
}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
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