Custom agent definition files
The 5-section agent file pattern. Two case studies from the TruPath team: AXIOM (QC engineering) and CIPHER (legal/IP).
Why agent files beat CLAUDE.md sections
Most operators start by adding specialist sections to their root CLAUDE.md. The logic is clean: one file, one place to look. Within three months, the file is 600 lines and contains fragments of four different roles. The agent reads all 600 lines on every session, allocates context to all four roles simultaneously, and loses coherence on every task that requires deep specialization.
The failure mode is not length — it is identity dilution. An agent with four roles active at once isn’t a specialist. It’s a generalist who has been told to pretend. AXIOM, the QC engineering director at TruPath, cannot do deep work on the RT-DETR-S CoreML export pipeline while simultaneously managing CIPHER’s IP sensitivity rules and SUMMIT’s SBA loan compliance checks. The cognitive load of all three domains degrades performance on each.
Separate agent files solve this by separating context at load time. When AXIOM is invoked, it loads its 200-line file and nothing else. The CV pipeline specs, the ESP32 firmware rules, the Supabase project reference, the CoreML export procedure — that’s all that’s in context. CIPHER’s rules about ACL and provisional patents are not in context unless AXIOM explicitly escalates to CIPHER. Specialization requires context isolation, not just labeling.
The TruPath agent team runs five agents at portfolio level — APEX (chief of staff), SUMMIT (MHG venue ops), VELOCITY (QC business strategy), AXIOM (QC engineering), CIPHER (legal/IP) — plus an additional 18-agent internal QC roster. Each has its own file. The routing rule lives in the root CLAUDE.md and is brief: a table of trigger words mapping to agents. The specialists carry the weight; the router stays lean.
The 5-section structure
Every agent file has five sections. The order matters — each section constrains the next. A file missing any section will have a predictable failure mode at the section it’s missing.
| Section | Contents | What breaks if it’s missing |
|---|---|---|
| 1 — Identity and domain | Who the agent is, what it owns, what it explicitly does not own, trigger words | Agent claims scope that belongs to other agents; trigger words fire in wrong contexts |
| 2 — Authority | “Can without asking” list, “must ask before” list, “never does” hard prohibitions | Agent asks permission for trivial operations; or acts on high-stakes decisions without asking |
| 3 — Tools and stack | Exact models, ports, endpoints, file paths, CLI commands — nothing generic | Agent guesses paths; uses wrong model; skips required pre/post steps like CoreML patch |
| 4 — Escalation triggers | Conditions requiring handoff or human review; named entities where applicable | Agent handles consequential decisions without routing; patent-sensitive work ships without CIPHER review |
| 5 — Routing | Which agents this agent sends work to and under what conditions | Work falls through gaps between agents; no handoff protocol for cross-domain tasks |
The tools and stack section is the most commonly under-specified. “The CV pipeline” is not a specification. “RT-DETR-S v10 CoreML running on :8642, CoreML export requires rtdetr_coreml_patch.py before export and validate_coreml.py after — no exceptions” is a specification. The difference is whether a new session can act correctly without asking for clarification on every tool call.
The rest of Expert · Lesson 12 is for subscribers.
Custom agent definition files (build AXIOM + CIPHER)
- Every Expert-tier lesson — diagnostic prompts, transcripts, prompt kits, full homework
- Every research paper — methodology, figures, tables, reproducibility appendices
- New Expert lessons + papers as they ship (quarterly cadence)
- Foundations + Operating lessons stay free; bundles on GitHub stay free; this tier is the deep stuff
Free while the early catalog ships. Paid tier comes later — subscribe now and you’re grandfathered in.