io.github.speedofred/ami-survey
ami-survey
Measures the cost, tokens and duration of a completed agent workflow from its session log.
alive probed 2026-10-14
14tools
3.9ktokens in Claude Opus 5.5
4.0ktokens in Claude Code
1.9 %of a 200k context window
2.2ko200k_base estimate
689 msto initialize
6 msto list tools
- Run it
- uvx ami-survey==1.2.0 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- ami-survey 1.2.0
- Capabilities
- tools
- Instructions
- 218 characters
- Claude count
- Claude Opus 5.5, measured 2026-10-14. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/speedofred/ami-survey-client-v1
- Website
- https://agentbenchmark.dev
- Registry
- active, updated 2026-09-09 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| ami_survey_begin | 452 | 20 % |
| ami_mark_stage | 278 | 12 % |
| ami_submit_survey | 260 | 12 % |
| ami_write_findings | 258 | 12 % |
| ami_record_calls | 253 | 11 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.speedofred/ami-survey)
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.