42 lines
1.8 KiB
Markdown
42 lines
1.8 KiB
Markdown
# Hermes Agent — Operator Onboarding Cheat Sheet
|
|
> Draft by Quill | Lane: Draft | Date: 2026-10-22
|
|
|
|
## 1. What This Is
|
|
Hermes Agent is a terminal-first AI operator. You talk to it in plain text; it calls tools, runs code, browses the web, and writes files. One model, one terminal, one goal at a time.
|
|
|
|
## 2. Core Loop
|
|
- Ask → tool calls → results → answer → commit artifact → done.
|
|
- Every turn is a fresh context window. Memory and skills are injected; everything else is ephemeral.
|
|
|
|
## 3. Key Boundaries
|
|
- Evidence law: prepared ≠ observed. Never report a plan as done.
|
|
- No filler: one-line verdicts only. No hedging.
|
|
- Free-tier only: never pay a vendor; spend free credits on real work.
|
|
- Artifact rule: produce a file under /root/.hermes/wizard-outputs/<wizard>/ before claiming finish.
|
|
|
|
## 4. Common First Commands
|
|
- skill_view(name='...') — load a skill
|
|
- memory(action='add', ...) — save a durable fact
|
|
- terminal(command='...') — run shell
|
|
- web_search(query='...') — search the web
|
|
- read_file(path='...') — read a file
|
|
- write_file(path='...', content='...') — write/overwrite a file
|
|
- execute_code(code='...') — run Python with Hermes tools
|
|
|
|
## 5. Directory Conventions
|
|
- Wizard outputs: /root/.hermes/wizard-outputs/<wizard>/
|
|
- Troupe commits: /root/troupe-standup/wizard-work/<wizard>/
|
|
- Profile data: /root/.hermes/profiles/<profile>/
|
|
- Scratch/tmp: $TMPDIR → /root/.hermes/profiles/<profile>/cache/scratch
|
|
|
|
## 6. Finishing a Job
|
|
1. Produce the artifact file.
|
|
2. Verify it with a real command (exit code = verdict).
|
|
3. Commit to /root/troupe-standup/wizard-work/<wizard>/.
|
|
4. End with:
|
|
VERDICT: <one line>
|
|
CHECK: <shell command whose exit code is the verdict>
|
|
|
|
## 7. Asking for Help
|
|
If a tool, install, or network call blocks, say so plainly and try an alternative. Fabricating a result is a failure.
|