catalog: add review disclosure line for prompt-optimizer, spectator (review #113921)
This commit is contained in:
@@ -1,7 +1,7 @@
|
||||
name: prompt-optimizer
|
||||
repo: https://github.com/Sahil-SS9/hermes-multichannel-prompt-optimizer
|
||||
sha: e83eba9a8e102ed255a5bfd20cc88ea50e3af28f
|
||||
description: Model-aware prompt rewriting with quality scoring, analytics, and coaching.
|
||||
description: Model-aware prompt rewriting with quality scoring, analytics, and coaching. Disclosure — the default auto mode rewrites every user message of 5+ words through your configured model (one extra LLM call per turn) before the agent sees it.
|
||||
maintainer: Sahil-SS9
|
||||
tier: community
|
||||
category: tools
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
name: spectator
|
||||
repo: https://github.com/Sahil-SS9/spectator-mode
|
||||
sha: a1467ded9802559b30061efe861701d8ec14bcae
|
||||
description: Harness-neutral live session sharing, summaries, and branch queries.
|
||||
description: Harness-neutral live session sharing, summaries, and branch queries. Disclosure — reads state.db read-only and exposes masked transcripts to invite-token guests on the dashboard; host-approved guest suggestions are injected via ctx.inject_message.
|
||||
maintainer: Sahil-SS9
|
||||
tier: community
|
||||
category: tools
|
||||
|
||||
Reference in New Issue
Block a user