Ibrahim Kobeissy

Local, read-only analytics for your opencode history. Run npx oc-lens and it finds your opencode database, opens a dashboard in your browser, and never writes a byte to your history.

It answers three questions:

• Where did the agent loop? The same failing command run four times, the same file re-read for nothing. Repeats are matched on tool and input, so ordinary work isn't flagged.
• What did my provider cost me? Rate limits, outages, broken streams, the retries opencode hides inside a step, and the cache price you lose when a call is resent.
• Where do the tokens go? By day, model, project, agent and session, priced with your own rates. If a model isn't priced, it says "not priced", never $0.00.

Also: full session replay with failures and loops marked in place, activity heatmaps, tool rankings, and JSON/ZIP export. MIT licensed, 100% local.

If you use Claude Code across many repos, your harness (skills, commands, subagents, hooks, settings.json, MCP servers, CLAUDE.md) gets copied by hand from project to project. The copies drift, nobody remembers where a skill came from, and risky ones slip in.

Harneo is an open-source desktop app (plus a CLI) that keeps one library of the artifacts you trust, imported from GitHub repos with a trust score and an audit. You build profiles from that library and install one into any project. Every install is previewed, backed up and reversible. It also notices when a project's files drift from the library, and Harnmap shows your setup as a factory map so you can test a new skill against it before you install it.

I run my own setup from it: 80 artifacts from 5 sources in my library. It's on v0.3.1, MIT, with Linux AppImage/.deb packages and source builds for macOS and Windows.