Hermes cron jobs should rely on durable state, not chat context
alexcovo_eth · x · 2026-08-15
Hermes Watcher highlights a common pitfall: writing prompts for Hermes cron jobs that only make sense within the current chat context. Since each cron run starts a fresh agent session, it cannot maintain conversation history. Instead, scheduled jobs should pull context from durable sources: the prompt defining the task, a Skill for repeatable procedures, and a Workdir for project context. Fragile commands like "Check on that issue" should be replaced by explicit instructions to run specific skills on defined project items.
More from coding & agent
- Dev's Cloud Agent experience: escaping pesky permission prompts — davidcrawshaw · 2026-08-15
- Verification test: Asking models to spec a local AI brain, only 1 cited real files — schwentker · 2026-08-15
- Tested 3 models to spec a local AI-brain install: one cited real files, one got macOS compat backwards — schwentker · 2026-08-15
- Claude Code CLI 2.1.233: Added Sandbox, GitLab MR Support — ClaudeCodeLog · 2026-08-15
- Claude Code 2.1.233 changelog: per-user spend headers, Bash memory cgroups, MCP fix — ClaudeCodeLog · 2026-08-15
- Claude Code v2.1.233 released: GitLab MR support and Linux memory limits added — ashwin-ant · 2026-08-15