Skip to main content

Documentation Index

Fetch the complete documentation index at: https://kensa.sh/docs/llms.txt

Use this file to discover all available pages before exploring further.

Run these from the root of your Python agent repo.

​
Paste this into your coding agent

Run `uvx kensa init --cli --agent all`, then use the audit-evals skill and
follow the eval lifecycle.
The agent installs the CLI, scaffolds .kensa/, drops in the five skills, and runs your first eval. Works with:

​
Or install yourself, then ask your agent

If you want to control the install step but still let your coding agent drive the eval workflow: 
uvx kensa init --cli --agent all
Then in Claude Code, Codex, Cursor, OpenCode, or Gemini CLI: 
> /audit-evals
The skill captures a real run, generates scenarios, runs evals, and reports back.

​
Or CLI-only

If you want to skip the coding-agent loop entirely and drive kensa as a regular CLI: 
uvx kensa init                                       # dev dep + bare .kensa/
kensa capture -i "<example input>" -- <your agent>   # record one real run as a trace
kensa generate                                       # synthesize scenarios from the capture
kensa eval                                           # run + judge + report
Add the SDK extra that matches your stack so traces include LLM calls and tool use: 
uv add "kensa[anthropic]"   # or kensa[openai] / kensa[langchain] / kensa[all]

​
What “evaluate this agent” actually does

audit-evals checks setup, then routes to the right next step: capture a real run, generate scenarios, calibrate a judge, or run evals. The CLI handles execution, tracing, judging, and reporting under the hood.

​
Next

  • Scenarios — write or generate test cases
  • Tracing — kensa capture and OpenTelemetry compatibility
  • CLI Reference — full command surface
  • Examples — runnable agents to point kensa at
Last modified on May 1, 2026