Skip to content llms.txt

Canonical Keys

Canonical keys are syllago’s cross-provider equivalents — the normalized names for fields, behaviors, and conventions that different AI coding tools express in their own ways. Each key below links to a detail page showing how every provider implements (or does not implement) that concept.

See format conversion for how keys translate between providers.

KeyDescription
agent_scopesWhere agent definitions can live and the priority ordering when definitions exist at multiple levels
definition_formatWhat format agent definitions use
invocation_patternsHow agents are triggered
model_selectionWhether per-agent model overrides are supported, allowing different agents to use different AI models
per_agent_mcpWhether agents can have their own MCP server configuration, scoping which external tools each agent can access
subagent_spawningWhether agents can spawn, delegate to, or resume other agents
tool_restrictionsWhether agents can be restricted to specific tools via allowlists, denylists, tool categories, or per-tool configuration maps
KeyDescription
argument_substitutionHow user-provided arguments are injected into command templates
builtin_commandsWhether the provider ships default/built-in commands alongside user-defined custom commands
KeyDescription
async_executionWhether hooks can run asynchronously without blocking the agent’s execution loop
context_injectionWhether hooks can inject messages, system prompts, or conversation context into the agent’s active session
decision_controlWhich decision actions hooks can take on the triggering action
handler_typesWhat kinds of executors hooks support beyond shell commands
hook_scopesWhere hooks can be configured and the precedence model when multiple scopes define hooks for the same event
input_modificationWhether hooks can modify tool input arguments before the tool executes
json_io_protocolWhether hooks communicate with the host via structured JSON on stdin/stdout rather than plain text or exit codes alone
matcher_patternsWhether hooks can filter which tools or events they respond to using name matching, regex patterns, or structured criteria
permission_controlWhether hooks can make or influence permission decisions determining whether a tool is available for invocation
KeyDescription
auto_approveWhether specific MCP tools or entire servers can be configured for automatic approval without per-invocation user confirmation
enterprise_managementWhether the provider supports organization-level MCP configuration management, including managed server lists, allowlists, and enterprise registries
env_var_expansionWhether MCP server configuration supports environment variable expansion
marketplaceWhether the provider offers an in-IDE MCP server discovery and installation experience
oauth_supportWhether the provider supports OAuth 2
resource_referencingWhether MCP resources (not just tools) can be accessed, typically via @-mention syntax or similar referencing mechanisms
tool_filteringWhich per-server tool filtering mechanisms the provider supports
transport_typesWhich MCP transport protocols the provider supports
KeyDescription
activation_modeHow rules decide when to load into context
auto_memoryWhether the provider auto-generates persistent rules from conversation context
cross_provider_recognitionWhich rule file formats from other providers this provider recognizes
file_importsWhether rules can reference or include content from other files
hierarchical_loadingWhether rules load from multiple directory levels with defined precedence
KeyDescription
canonical_filenameThe required or conventional filename for this skill type
compatibilityProvider compatibility constraints — which AI tool versions or providers this skill is compatible with
custom_filenameWhether the provider supports custom filenames (beyond the canonical filename convention)
descriptionWhat the skill does
disable_model_invocationWhen true, the AI cannot auto-invoke this skill; only the user can invoke it explicitly
display_nameHuman-readable display name for the skill
global_scopeWhether the skill can be installed at global/personal scope (applies across all projects for the current user)
licenseSPDX license identifier for the skill content
metadata_mapArbitrary key-value metadata attached to the skill
project_scopeWhether the skill can be installed at project scope (applies to current project only, typically committed to version control)
shared_scopeWhether the skill can be installed at shared/enterprise scope (applies to all users in an organization or shared environment)
user_invocableWhen false, the skill is hidden from user-facing menus (e
versionSemantic version string for the skill