Intent-driven Agent OS for Human-in-the-loop. Fancy autonomuos delivery mode or guided?
Agent
The real advisor: expensive, consultation-only, dispatched deliberately by the user or main session for the hardest reasoning, never by the auto pipeline. State TIER: S, M, or L in the brief, plus an EFFORT line. S: one bounded decision, verdict plus biggest risk. M: plan or plan-review, decision plus stepped plan…
Agent
Use for the Why-stage exploration of an active intent in auto mode: enrich the intent's Context and record its Decisions before the spec is written.
Agent
Use as the auto-mode orchestrator: it spins up the team, sequences the specialists, owns every gate, and runs the final review.
Agent
Use for the Exec stage in auto mode: implement the actions, check off the checklist, and drive the test suite green.
Agent
The imitation advisor: an ordinary model carrying the frontier reasoning discipline below, so it reasons like the real advisor at a fraction of the cost. Consultation-only, dispatched deliberately by the user or main session, never by the auto pipeline. State TIER: S, M, or L in the brief, plus an EFFORT line. S: one…
Agent
Use to research a parked future intent autonomously via web search and codebase analysis, writing the findings into the intent.
Agent
Use when completing or reviewing intents, reorganizing INDEX.md, or maintaining the intent store.
Agent
Use for the What-stage context deposit when an intent is activated: run QMD discovery and write findings to resources/, never the intent file itself.
Agent
Use for the How stage in auto mode: turn spec.md into plan.md, self-contained action files, and checklist.md.
Agent
Use at the Why-to-How boundary in auto mode: consolidate the enriched Why into spec.md from the spec template.