io.github.cuonztech/agent-harness
cuonztech-agent-harness
MCP chaos-testing toolkit. Default: simulated demo. Configure proxy mode to test a real agent.
alive probed 2026-10-14
7tools
1.9ktokens in Claude Opus 5.5
2.0ktokens in Claude Code
1.0 %of a 200k context window
1.1ko200k_base estimate
295 msto initialize
9 msto list tools
- Run it
- npx -y cuonztech-agent-harness@0.5.2 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- cuonztech-agent-harness 0.5.2
- Capabilities
- tools
- Instructions
- none
- Claude count
- Claude Opus 5.5, measured 2026-10-14. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/cuonztech/agent-harness
- Registry
- active, updated 2026-10-13 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| start_session | 515 | 47 % |
| execute_call | 156 | 14 % |
| get_score | 155 | 14 % |
| get_report | 107 | 10 % |
| reset_session | 67 | 6 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.cuonztech/agent-harness)
An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.