Repeated repo discovery
Agents keep asking which test command, build command, or diagnostic command applies.
Every workspace has ceremony: how to build, test, search, diagnose, scaffold, promote, and recover. AXF turns that ceremony into small, self-describing capabilities an agent can inspect and run.
It is not a universal command catalog. It is a workspace-owned exoskeleton for the agent operating inside that workspace.
axf doctor
axf list
axf inspect echo say
axf run echo say --message hello
# MCP entrypoint
axf mcp
Agents keep asking which test command, build command, or diagnostic command applies.
Important rules live in prose, convention, or human memory instead of inspectable capability metadata.
Common chores are rebuilt turn after turn instead of promoted into stable capability contracts.
Inspect a workspace and identify candidate capabilities or missing local bearings.
Ask what a capability is, what arguments it expects, and how AXF would launch it.
Execute known capabilities through AXF's adapter path instead of raw shell fallback.
Create draft capabilities and adapters that can be reviewed before becoming active.
Move capabilities through lifecycle states when they are ready for agents to rely on.
Expose one axf MCP tool that routes into the same capability surface.
AXF separates the root used to discover capability manifests from the root where execution should occur. In simple repos they are the same. In more advanced agent setups, the execution root can be a contained work area while the project root remains the canonical capability registry.
{
"env": {
"AXF_PROJECT_ROOT": "/path/to/project",
"AXF_EXECUTION_ROOT": "/path/to/execution-root"
}
}