Why a Specialized Agent Is Just an 8-File Preconfigured Harness Component Pack
You do not need a custom model checkpoint or a new Python framework to build a domain-specialized agent. Every specialized agent on getagentfoundry.si is a portable 8-file harness bundle.
Teams often assume that building a specialized agent for 3D WebGL geometry, statutory compliance screening, or distributed-systems verification requires either fine-tuning a model checkpoint or writing a bespoke orchestration daemon. In our Harmony study (harmony.baltor.ai and agents.baltor.ai), we proved that a domain-specialized agent is completely determined by an 8-file preconfigured harness component pack mounted around a fixed open-weight or frontier model.
The canonical 8-file pack layout
Every task agent published on getagentfoundry.si (and indexed across foundry.baltor.ai) ships as a deterministic directory containing eight files with strict byte budgets:
| File Name | Max Budget | Architectural Role in the Six-Part Harness |
|---|---|---|
baltor_contract_card.json |
<= 2,048 B |
Context / Discovery: Typed input/output ports, engine slot ID, refusal codes, and verifier SHA-256. |
AGENTS.md |
<= 4,096 B |
Control Loop: Role identity, execution boundaries, and stop conditions. |
SKILL.md |
<= 6,144 B |
Context (H_env): Verified domain algorithms, mathematical formulas, and reference snippets. |
RULES.md |
<= 3,072 B |
Context (H_gen): Numbered non-negotiable invariants checked on every turn to prevent middle-rule drop. |
WORKFLOW.yaml |
<= 2,048 B |
State & Loop Graph: Ordered Loop steps, call budget ceiling, and fallback recovery policy. |
TOOLS.json |
<= 4,096 B |
Action: Typed tool schemas with path confinement and taint-tracking annotations. |
verifier.py |
Executable | Verification (worker != verifier): Independent AST, physics, and known-wrong conformance gate. |
README.md |
Human docs | Setup prerequisites, what success looks like, and failure recovery steps. |
Why factorizing SKILL.md, RULES.md, and verifier.py works
When instructions, domain math, and verification logic are mixed into a single unstructured system prompt, the model treats hard constraints as optional style suggestions. Separating RULES.md (numbered invariants) from SKILL.md (verified reference implementations) and enforcing verifier.py out-of-band ensures that no candidate output is promoted until every numbered rule passes execution.
| Navigation | Post Title | Routes |
|---|---|---|
| Previous Post | Cross-Harness Export: One Component Pack Across Claude Code, Codex, and Ollama Cloud | HTML · Markdown |
| Next Post | Rule 6 in Practice: Wrapping Open-Source GitHub Projects Behind Typed Engine Slots | HTML · Markdown |
| Domain Blog Index | Return to getagentfoundry.si/blog Index | feed.json · feed.xml |