Skip to main content

Discover what is installed

nasiko status prints the active cluster’s health, then one row per supported harness on this machine. The harness rows come from the local machine only: they change no harness settings and print even when no cluster is reachable.
A config directory with no binary still counts as installed: it means the harness was used on this machine before. For one harness in detail, including where its reporting hook lives, run nasiko status <agent>.

Set up every harness at once

setup needs an active cluster and a current login (nasiko auth login). On a terminal, nasiko auth login, nasiko connect <cluster-url>, and nasiko use <cluster> also offer to turn on reporting for the harnesses they find. setup does two things:
  1. Connects every detected harness that has no reporting yet, exactly as connect --reporting would, with content capture on. One harness failing doesn’t stop the others: you get a warning and the command to retry.
  2. Imports past sessions from those harnesses, newest first, in the background. Imported turns are delivered the same way as new ones.
Follow a background import with nasiko agents status, which shows its progress, what is still waiting to send, and the end of its log. The Coding harnesses page in the dashboard follows it too. Only one import runs on a machine at a time. To import again later for harnesses that are already connected, run nasiko agents import. setup never rebinds a harness that already reports, and keeps its content setting. If you switch clusters, a harness you connected earlier keeps reporting to its original cluster. To move it, select it when nasiko connect <cluster-url> or nasiko use <cluster> lists it as reports sessions to <cluster>; select to move it here. Or run nasiko connect <agent> --no-routing --reporting while the new cluster is active. To leave prompt and response text out for a harness, connect it with --no-content first, then run setup. Imported sessions follow the same setting.

Turn on session reporting for one harness

nasiko connect <agent> sets up any of LLM routing, MCP connectors, and session reporting. On a terminal, nasiko connect claude with no flags asks about each one. The flags above turn on reporting only and skip the questions. For every flag, see Connect a coding agent. Reporting needs an active cluster and a current login (nasiko auth login). Turning it on does three things:
  1. Registers the harness with your Nasiko cluster, or finds the existing registration.
  2. Adds a reporting hook (or plugin, for OpenCode) to the harness config directory.
  3. Saves a local install record that binds reporting to the cluster and user that are active right now.
--no-content reports tokens, latency, models, and tool metadata but leaves out prompts, responses, session titles, and tool inputs and outputs. See what is captured. A cluster that doesn’t keep chat history gets usage only, whatever you choose. Some harnesses need one more step:
  • Codex: open Codex, run /hooks, and trust the new Nasiko command hooks.
  • OpenCode: restart OpenCode so it loads the new plugin.
Then start a new session in the harness. Completed turns show up in Sessions in the dashboard, and in nasiko sessions and nasiko observe sessions. Turning on reporting fails if the harness is not detected on the machine, if you are not logged in, or if the harness config file it needs to edit is not valid JSON.

Cluster binding

Each install is bound to the cluster name, cluster URL, and user that were active when you turned reporting on. Every turn is queued for that destination and no other. Nasiko never reroutes queued turns to a different cluster or user. To change the binding, or to switch --no-content on or off, run nasiko connect <agent> --no-routing --reporting again with the cluster you want active, adding --content or --no-content. Turns queued before that stay bound to their original destination. See cluster or user changes.

What registration creates

Registering a harness creates one coding-agent identity per harness per user on your Nasiko server. Registering again returns the same identity. The identity is owned by you and tagged local and coding-agent. Reported sessions and routed model calls are both attributed to it, so cost rolls up by harness and developer. Model routing reuses the same identity.

Where coding agents appear in the dashboard

  • Agents lists each registered coding agent under its label, such as Claude Code ([email protected]), alongside your deployed agents. Nothing runs on Nasiko for a coding agent, so its agent page has no Configure or Logs tab.
  • Sessions lists reported coding sessions next to your other chats. A coding-agent session opens read-only, with the note “This is a recorded coding-agent conversation. Continue it in the original coding agent.”
  • Observability shows the same sessions with traces, tokens, and latency.
  • TokenOps shows their cost. See TokenOps dashboard.
From the CLI, nasiko agents ls lists registered coding agents with the same label.

Turn off session reporting

disconnect --reporting removes the Nasiko hook entries from the harness config, deletes the hook script, and removes the local install record. It leaves everything else in the harness config alone. The coding-agent identity and its past sessions stay on the server. Turns already in the local queue are still delivered. --reporting alone doesn’t change model routing; add --routing to remove that too. For every flag, see the coding agents CLI reference.