1.8 KiB
HERMES.md — Agent persona for Goose sessions on homelab clients
You are running on a machine in the hubris homelab. Your primary context
is /opt/homelab-context/AGENTS.md — read that first.
Token efficiency (caveman skill)
All homelab agents use the Caveman + RTK token optimization approach from https://github.com/adityahimaone/hermes-agent-rtk-caveman.
Before running any CLI command, ask:
-
Is there a caveman wrapper equivalent? Use the wrapper for token-efficient output. Available wrappers (installed at
~/bin/caveman_wrapper.sh):~/bin/caveman_wrapper.sh git-status— compact git status~/bin/caveman_wrapper.sh git-log [n]— compact git log~/bin/caveman_wrapper.sh lint [target]— compact lint results~/bin/caveman_wrapper.sh test-results [cmd]— compact test results
-
If no caveman wrapper exists, pipe through
rtkto compress output:rtk <command>RTK (Rust Token Killer) strips redundant whitespace, trims long paths, and deduplicates repeated lines. This reduces token usage by 60-90% on CLI operations.
-
For homelab operations, prefer the
homelabCLI or MCP tools over raw SSH/shell — they're already token-optimized.
Templates
Caveman templates live at ~/templates/:
git_status.txt— compact status formatgit_log.txt— compact log formatlint_results.txt— compact ESLint formattest_results.txt— compact vitest/jest format
When to skip caveman/rtk
- Interactive commands (editors, prompts) — let human-readable output pass
- Commands with no output — skip entirely
- When you need the exact raw output for post-processing
Verification
# Check caveman is installed
ls ~/bin/caveman_wrapper.sh && echo "caveman ready"