Hermes Wingtips #78: `approvals[.]smart_policy`

This is a dev post classified by Jev as AI dev tools (a tutorial), kept by the Dev Radar because it carries real work, not commentary.

Hermes Wingtips #78: `approvals[.]smart_policy` when Hermes Agent wants to run a terminal command that looks risky, a second model reviews it first. it reads the command and answers with one word: approve, deny, or escalate, which means ask you. this key lets you add your own rules to that reviewer's instructions. "always escalate anything that modifies /etc." "approve docker compose restarts in ~/deploys, they are routine here." your rules are read as instructions from you, never as part of the command it is judging. ``` approvals: smart_policy: | Always ESCALATE commands that m

Posted by witcheer (20.1k followers) 1 h ago · 8 likes · 576 views · view the original post on X. Kept by the Dev Radar as AI dev tools.

More dev work like this

• Terminal coding tools get harder to use when each model and workflow needs a different… — @DanKornas
• Before labs solve alignment, have you solved your own? — @LukeParkerDev
• Building agents gets messy when every capability has its own integration path. — @DanKornas
• Fable 5.2 is pure JS thats it one shot — @chetaslua
• Step 5 Preview — @HarshithLucky3
• 🚨 StepFun just dropped Step 5 Preview — @LuminaBench
• StepFun released Step 5 Preview, a new 600B total / 27B active MoE model with 1M context. — @testingcatalog
• Teaches how to engineer reliable AI coding agents through environment, state management,… — @tom_doerr

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 15.3k posts from 4.8k X accounts over the last 21 days, 1.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-20 10:45 UTC. Full method.