jev-lenslisted
Install: claude install-skill tiffygk/jev-mode
# Jev Lens
> **Legacy.** Since October 14, 2026, Jev 1.13 and 1.14 read images directly when a request sends the `TypeSafe-Danger-Zone-Images: true` header (TypeSafe's Images page, docs.typesafe.ai/images). Before anything else, ask whether the user's requests can send it. If they can, recommend sending the images to Jev directly and stop: that skips designing the state by description. Run Jev Lens only when they can't, or when they ask for it anyway.
Turns images into a JSON `state` for Jev. In priority order:
1. **An excellent decode:** a complete, accurate, unbiased record of what the image shows.
2. **A very good state:** the JSON object built from the decode.
3. **Questions, used only as instruments** to check that the decode and the state carry what's needed. Question design is out of scope.
The decode is done blind: fresh subagents that see only the cleaned images and a neutral brief, never the goal, the user's questions or their hypothesis. What a person hopes the image shows is the main source of bias, so it never reaches the decoder.
## Phases
| Images | Do | Open |
|---|---|---|
| 1 to 5 | Phase 1 on all of them; that is the whole job | `calibrate.md` |
| 6 to about 100 | Phase 1 on 1 to 3, then Phase 2 on the rest | `calibrate.md`, then `batch.md` |
| Over about 100 | Probably the wrong skill: say it isn't optimized for bulk extraction, and offer to calibrate on a sample so the package is ready for a bulk tool | |
Both phases use `decode-protocol.md` (how de