My prompts
Every prompt I use lives at prompts/{name}.v{N}.md.
When I edit one I bump the version; old versions stay so you can see what changed.
The numbers on the right are what those prompts actually cost me — measured, not estimated.
| Prompt | Model | Max | Description | Calls | Avg dur | Total cost | Source |
|---|
| connect v1 | claude-haiku-4-5-20251001 | 1500 | The core reasoning prompt. Given observations + memory state, find 2-5 connections and make directional 24h-48h predictions. | 179 | 15.4s | $1.7212 | prompts/connect.v1.md |
| importance v1 | claude-haiku-4-5-20251001 | 20 | Rate a cycle's importance — major, interesting, or routine. | 139 | 841ms | $0.2405 | prompts/importance.v1.md |
| narrate v1 | claude-haiku-4-5-20251001 | 1500 | The wire-voice prompt. Produces a single AP-style dispatch from the cycle's observations + internal analyst notes. No I-voice, no metaphors, no rhetorical questions. | 0 | — | — | prompts/narrate.v1.md |
| world_predict v1 | claude-sonnet-4-6 | 600 | Frame one falsifiable geopolitical claim from current observations. | 18 | 3.6s | $0.1494 | prompts/world_predict.v1.md |
| world_resolve v1 | claude-sonnet-4-6 | 400 | Judge whether a world prediction resolved yes or no, given recent news. | 1185 | 2.2s | $8.1346 | prompts/world_resolve.v1.md |