dilim/hermes-agent
1
0 Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-11-06 05:17:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore(catalog): review disclosure for enhance-prompt

Browse Source
This commit is contained in:
Teknium committed 2026-11-05 10:32:57 -08:00
1 parent f6ab1e1796
commit 0bc1eaec12
1 file changed
+1 -1
Download Patch File Download Diff File Expand all files Collapse all files
plugin-catalog/enhance-prompt.yaml
+1 -1
View File
@@ -4,7 +4,7 @@ sha: 8417827ff80db2335e18742c1f5317aeb4b036cb
version: "0.7.0"
requires_hermes: ">=0.21.5"
title: Enhance Prompt
description: "A sparkle beside Send that rewrites the composer draft in place without sending it, deepening it into a clarifier, a task list, then a phased plan on further clicks, with a one-click discard back to the original. Also registers the `/enhance` slash command and the `enhance_prompt` tool for the same rewrite from the agent. Draft read and write go through `host.composer`, so `@file` and `/command` chips survive. Disclosure — every click runs one stateless `llm.oneshot` call on your own gateway with the current chat's model, plus an optional second short call to score the result, so it spends your model credits. It is not an agent turn: no tools run and nothing is written to a session you cannot see. It overrides no model, sends nothing to a third party, never sends the composer message, and carries no telemetry, no credentials and no self-update."
description: "A sparkle beside Send that rewrites the composer draft in place without sending it, deepening it into a clarifier, a task list, then a phased plan on further clicks, with a one-click discard back to the original. Also registers the `/enhance` slash command and the `enhance_prompt` tool for the same rewrite from the agent. Draft read and write go through `host.composer`, so `@file` and `/command` chips survive. Disclosure — every click runs one stateless `llm.oneshot` call on your own gateway with the focused chat's model (the auxiliary title model when no chat is focused), followed by a second short call to score the result, so it spends your model credits. It is not an agent turn: no tools run and nothing is written to a session you cannot see. It overrides no model, sends nothing to a third party, never sends the composer message, and carries no telemetry, no credentials and no self-update."
maintainer: tuancookiez-hub
tier: community
category: desktop