Skip to main content
The CLI ships with a minimal, structured output mode (--prompt-only) designed for AI coding agents to parse and act on. Combined with a team key, it enables autonomous review-fix loops — the agent reviews, applies fixes, re-reviews, and commits, all without human input in the critical path.

​
Supported agents

  • Claude Code — native skill via the skill installer.
  • Cursor — native skill.
  • Codex — native skill, with Decision Memory via notify hooks.
  • Windsurf — via --prompt-only output.
For any other agent that can run shell commands and parse structured text, kodus review --prompt-only works out of the box.

​
Quickest setup

Install the CLI plus all agent skills in one shot:
This:
  1. Installs the @kodus/cli binary globally.
  2. Configures the team key in ~/.kodus/config.json.
  3. Deploys Kodus skills to every detected agent (Claude Code, Cursor, Codex, Windsurf).
No individual logins. No interactive prompts. Ready for agent loops immediately.

​
The Review-Fix Loop

1

Agent runs review

The CLI returns structured issues with file paths, line numbers, severities, and suggested fixes — in a compact text format designed for an LLM to consume.
2

Agent applies fixes

The agent reads the output, decides which fixes to apply (or accepts all via --fix), and edits files accordingly.
3

Agent re-runs review

With --fail-on error, the loop exits non-zero while there are still error-or-worse issues. The agent keeps looping; when the review comes back clean, the process exits 0 and the agent moves on.
4

Agent commits and pushes

Once the review is clean, the agent commits and pushes. Optionally, install the pre-push hook (kodus hook install) for an additional safety net on manual pushes.

​
Team key authentication for agents

Team keys are strongly recommended for agents — no individual signup, no interactive login, easy rotation, per-device tracking.
Generate a key at app.kodus.io/organization/cli-keys and distribute the install command shown there to your team.
Save the key when it’s shown — it won’t be displayed again.

​
Output flags that matter

​
Combining with Decision Memory

Pair agent loops with Decision Memory to capture the reasoning behind every agent turn as structured files in your repo. The loop handles what changed; memory captures why.

​
Example: Claude Code loop with business validation

With the skill installer, Claude Code’s Kodus skill knows when to invoke each of these — no prompt engineering required on your side.

Decision Memory

Persist agent decisions as structured files in your repo.

Concepts

Review modes, diff modes, and agent output flags.

Command Reference

Full flag listing.

Troubleshooting

Agent loop issues, hook problems, timeouts.