hermes-context-file-loading

Topics in the source

• Hermes Context File Loading
• When to use this skill
• The one table that matters: file → mechanism
• Critical precedence rule (project context = ONE slot)
• Prompt-assembly tiers (cache discipline)
• Hard facts to design around
• Decision shortcut
• Verification recipe (re-confirm after Hermes upgrades)

How Hermes builds its system prompt from instruction files. Mechanics here override any vibe-based assumption — when in doubt, re-read the loader functions in $HERMESHOME/hermes-agent/agent/promptbuilder.py and the runtime's context-files docs page (user-guide/features/context-files/). Function names are stable; line numbers drift between versions, so locate by name. Auditing / editing SOUL.md, AGENTS.md, MEMORY.md, USER.md, or any context file. Deciding which layer a durable rule belongs in (identity vs project vs memory). Debugging "why did/didn't this instruction file take effect?" Reasoning about subagent context, cwd dependence, or prompt-cache stability. For a step-by-step audit + surgical de-dup procedure (backup → verify-paths → owner decisions → collapse-duplicates-to-pointer → memory-cap handling → verify), see references/auditing-instruction-files-workflow.md. Run it whenever the owner asks to clean, de-dup, or fix conflicts across the four instruction files. | File | Loader fn (promptbuilder.py) | Discovery scope | git? | Global? | |------|--------------------------------|-----------------|------|---------| | SOUL.md | loadsoulmd() | HERMESHOME/SOUL.md ONLY — never prob

This is an excerpt. Refer to the complete source and its current requirements.