Asset Types
Asset type vocabulary, naming conventions, and ecosystem mapping for bundle assets.
Overview
Asset types are free-form strings, not an enum. The asset_type field
on BundleAsset accepts any string up to 50 characters. This design allows the type vocabulary
to evolve as the agent ecosystem grows, without requiring schema migrations.
Recommended Types
| Asset Type | Description | Ecosystem Equivalent |
|---|---|---|
prompt | System instructions, guidelines, or standalone prompt text | CLAUDE.md, AGENTS.md, .cursorrules, copilot-instructions.md |
rule | Modular rule files with optional path-scoping metadata | .claude/rules/*.md, .cursor/rules/*.mdc, .roo/rules-*/*.md |
skill | Composable skill definitions (SKILL.md + supporting files) | .claude/skills/*/SKILL.md, Agent Skills standard |
agent_spec | Agent or mode definitions with tool permissions and behavior | .claude/agents/*.md, .agent.md, .roomodes |
toolset | Tool policies and MCP preset configurations | .mcp.json, .cursor/mcp.json, .amazonq/mcp.json |
template | Parameterized templates for code generation or scaffolding | Prompt templates, .prompt.md files |
config | Tool settings, environment config, or operational parameters | settings.json, config.toml, .aider.conf.yml |
schema | JSON Schema, OpenAPI fragments, or data shape definitions | Validation schemas, API contracts |
Naming Conventions
- Use lowercase with hyphens for multi-word types (e.g.
mcp-config, notmcpConfigorMCP_CONFIG). - Keep types short and descriptive — the 50-character limit is generous but brevity aids readability.
- Prefer singular nouns (
prompt, notprompts).
Ecosystem Context
The recommended types above are derived from a survey of ten major agent harnesses (Claude Code, Codex CLI, Cursor, Windsurf, Aider, GitHub Copilot, Cline, Roo Code, Amazon Q, Gemini CLI). Despite different naming conventions, the functional categories collapse to roughly the same set:
- Instructions and prompts — every tool supports markdown-based instruction files.
- Modular rules — 7 of 10 tools support multiple rule files loaded by directory scan.
- Skills — the Agent Skills standard (SKILL.md) has reached 8 of 10 tools.
- Agent definitions — role-based agent/mode configuration is supported by most tools.
- MCP server configs — 9 of 10 tools support MCP, making it near-universal.
None of these tools provide built-in versioning for their configuration files. Bundles fill this gap by offering immutable, SHA-256-verified snapshots of asset collections.
Asset Support Matrix
How asset categories map across the ten surveyed agent harnesses. A tool name indicates documented support for that category.
| Category | Bundle Type | Supported By |
|---|---|---|
| System instructions | prompt | All 10 harnesses |
| Modular rules | rule | Claude Code, Cursor, Windsurf, Roo Code, Cline, Amazon Q, GitHub Copilot |
| Skills / commands | skill | Claude Code, Codex CLI, Cursor, GitHub Copilot, Cline, Roo Code, Windsurf, Gemini CLI |
| Agent / mode definitions | agent_spec | Claude Code, Codex CLI, Cursor, GitHub Copilot, Roo Code, Amazon Q, Gemini CLI |
| Tool policies & MCP presets | toolset | All except Aider (9 of 10) |
| Templates | template | GitHub Copilot (.prompt.md), general-purpose |
| Settings / config | config | All 10 harnesses (varying formats) |
| Schemas | schema | General-purpose (validation, API contracts) |