ibahgat

Use for architecture decisions, boundaries, and technical tradeoffs before implementation.

Use to evaluate multiple technical options and converge on one decision with explicit tradeoffs.

Use for decision criteria design, strategic analysis, and recommendation framing across technical or business tasks.

Use for failures, flaky behavior, stack traces, and root-cause analysis.

Use to orchestrate multi-role team communication, conflict resolution, and lifecycle handoffs.

Use to transform multi-agent outputs into structured, concise, audience-fit deliverables.

Use for focused implementation, refactoring, and test updates once a plan exists.

Use to break a request into ordered phases, tasks, and validation checkpoints.

Use to create PRD-quality scope, constraints, acceptance criteria, and non-goals before implementation.

Use for very small, low-risk edits like typo fixes, tiny refactors, and formatting.

Use for documentation lookup, API comparisons, and evidence-based technical decisions.

Use for code review focused on correctness, regressions, security, and missing tests.

Use for acceptance-gate verification, test evidence checks, and release-readiness decisions.

Set omi approval posture (`suggest`, `auto`, `full-auto`) with explicit risk guardrails.

Run autonomous multi-stage execution loops until acceptance criteria pass or blockers are reached.

Gracefully stop active autonomous workflow, preserve progress, and produce a resume-ready handoff.

Compare multiple implementation options and converge on one decision with explicit tradeoffs.

Improve context efficiency and cache stability for long or complex sessions.

Initialize long-session context with a deep repository map, validation hooks, and risk hotspots.

Run omi readiness diagnostics for commands, skills, state files, and team/hook safety posture.

Implement a scoped task quickly and safely, then validate and summarize changes.

Operate omi's extension-native hook pipeline with deterministic triggers, safety gates, and efficiency budgets.

Control omi visual HUD profile and keep status output readable in normal, compact, or hidden mode.

Classify user intent and route work to the correct omi stage before execution starts.

Enforce repeated exec-verify-fix cycles until acceptance criteria pass or blockers are explicit.

Manage durable project memory with MEMORY.md index, topic files, and modular rule packs.

Inspect or switch omi operating mode/profile for speed, depth, autonomy, or strict quality gates.

Create a phased implementation plan with risks, dependencies, and validation checkpoints.

Convert a request into PRD-quality scope, measurable acceptance criteria, and delivery constraints.

Run strict quality-gated orchestration where every completion claim must pass verification gates.

Create a strict, quality-first execution plan with explicit gates and rollback-ready sequencing.

Control omi reasoning effort level to balance depth, rigor, latency, and token cost.

Run source-backed technical research and convert findings into implementation-ready guidance.

Inject conditional rule packs (tests, migration, security, docs, perf) based on task signals.

Assemble a task-fit Agent Team dynamically, request approval, then execute the staged lifecycle.

Coordinate the full omi stage pipeline across sub-agents for complex delivery (plan -> prd -> exec -> verify -> fix).

Deliver many independent tasks quickly with shard-based execution and periodic quality gates.