Human-first is the AI integration
magus was built for humans, and agents drive it well anyway, because an interface legible to a person is legible to anything. That ordering is the design, and the reason underneath it is structural: models learned to use tools from decades of humans using tools, so a tool that honors the conventions humans settled (exit codes, a working directory that means what it means everywhere, a path as a project's name, plain text) inherits agent competence for free. A tool that invents its own dialect fails both audiences, then watches the models learn its workarounds forever. Buzz is the evidence we have: a language with close to no training data produces better agent output than the most-trained languages on earth, with explicitness the only variable in sight. Weigh that as experience rather than benchmark; it is still the strongest evidence in this section.
This prevents the bolted-on AI integration, papering over a tool people already struggle with, and the quiet inversion where a person becomes the secondary user of their own build tool.
The floor under the ordering rule is an absent seam: magus never calls a
model (Scope records the missing adapter as
deliberate), and no CLI flag exists to feed one: every command and its output
are for the person who typed it, and what an agent reads it reads through the
MCP tools. Every review capability is a person's to run with no agent
anywhere in the loop; the agent integration is additive, never load-bearing.
The installed skills are gitignored renderings of the binary, so nothing in
CI can drift-gate them; magus doctor's agent-skills check is what observes
staleness, per workspace (Scope). A
workspace that goes a day, or a Friday, without an agent loses nothing but
speed.
Enforced by
- An ordering rule with one worked example: the
agentskey inaffected ci --planis the one agent-specific field in an otherwise human-first plan, and the skill-routing hint sits quarantined inside it. - The one deliberate exception is the job store, an agent-to-agent declaration
under Agents propose, humans dispose:
written by agents through MCP and read by people at
magus ls jobs, so the asymmetry is in who ordinarily authors it, not in who may see or write it. magus doctor's agent-skills check reports a stale installed skill.
Good
One flag, one output contract, for whoever is reading:
magus affected ci --plan -o json
Bad
magus affected ci --plan --for-agent --llm-summary
A flag shaped for a model splits the output into two dialects. The person's copy and the agent's copy drift, and the agent learns a form no person ever reads or checks.