ito

Implement Ito Lite markdown changes by reading proposal/spec/design/tasks artifacts and updating manual task statuses. Use when applying or executing a prompt-only Ito Lite change without the ito CLI.

Archive completed Ito Lite changes by manually merging spec deltas into current specs and moving the change to archive. Use after implementation and verification when no ito CLI is available.

Create prompt-driven Ito Lite change proposal packages in markdown. Use for drafting proposal.md, spec deltas, optional design.md, and tasks.md without the ito CLI or validation executable.

Review Ito Lite markdown proposal packages before implementation. Use to check proposal.md, spec deltas, design.md, and tasks.md for consistency, risk, testability, and manual validation without the ito CLI.

Initialize a markdown-only Ito Lite workspace with no executables. Use when setting up prompt-driven change proposals, creating .ito-lite/project.md, or preparing a repo for Ito-style specs, changes, and tasks without the ito CLI.

Coordinate the prompt-only Ito Lite workflow for proposals, specs, tasks, reviews, implementation, and archive without the ito executable. Use when the user asks for Ito-style planning, change proposals, lightweight specs, or markdown-only change management.

Balanced skill for typical development tasks, code review, and implementation work

Coordinator-only agent for orchestrating multi-change runs

Plans Ito orchestration runs from change metadata and gates

Fast, cost-effective skill for simple tasks, quick queries, and small code changes

Read-only researcher for Ito orchestration context gathering

Reviews Ito orchestration gate results and worker changes

High-capability skill for complex reasoning, architecture decisions, and difficult problems

Implements Ito orchestration work packets and remediation tasks

Apply a Change Proposal. Triggered by the user saying "Apply change <change-id>" or "Implement change <change-id>". Use when implementing, executing, applying, building, coding, or developing a feature, change, requirement, enhancement, fix, or modification. Use when running tasks from a spec, proposal, or plan.

Archive a completed change and update main specifications. Use when the user has finished implementing and wants to integrate the change into the main codebase.

Use for open-ended design exploration and idea refinement before scoping a concrete Ito change.

Find and remove legacy Ito-managed files left behind by older Ito versions. Use when a repo may contain stale or renamed Ito skills, commands, prompts, adapters, or planning artifacts.

Create atomic git commits aligned to Ito changes. Use when you want to commit work after applying a change, optionally with auto-mode.

Start a feature-oriented Ito change proposal with feature-biased intake and schema recommendations.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work — presents structured options for merge, PR, or cleanup

Start a fix-oriented Ito change proposal with fix-biased intake and schema recommendations.

List Ito changes, archived changes, specs, or modules with status summaries and intelligent interpretation.

Run an ito ralph loop for a change, module, or repo-ready sequence, with safe defaults and automatic restart context on early exits.

Use Ito's configured memory provider to capture, search, and query project knowledge. Activate when users ask to remember, recall, search memory, query memory, save learnings, or use Ito memory. Provider-agnostic: routes through `ito agent instruction memory-capture`, `memory-search`, and `memory-query` rather than calling ByteRover or another backend directly.

Set up orchestration defaults, presets, and workflow guidance for a repo.

Coordinate multi-change runs with gates, run state, and remediation.

Optional repo-specific supplement for orchestrators after `ito agent instruction orchestrate` has been loaded.

Use when you need stable absolute paths (project/worktree/.ito/worktrees) without embedding machine-specific paths into committed files

Exploratory, question-driven planning before creating Ito change proposals. Use when an idea needs shaping, scoping, sequencing, or research before proposal scaffolding.

Clarify a requested change before scaffolding a proposal, then recommend the next workflow lane and schema.

Use when creating and writing an Ito change proposal (new change or existing change id). Delegates to Ito CLI instruction artifacts.

Conduct structured research for feature development, technology evaluation, or problem investigation. Use when the user needs to explore options, analyze trade-offs, or investigate technical approaches.

Review and validate Ito changes, specs, or implementations. Use when the user wants a quality check, code review, or validation of project artifacts.

Unified entry point for ito commands with intelligent skill-first routing and CLI fallback.

Use for sequential per-task subagent delegation within one Ito change in the current session.

Use Ito tasks CLI to manage tasks.md (status/next/start/complete/shelve/add).

Use when tests need to be run with minimal output noise and delegated execution; routes test runs through the dedicated ito-test-runner subagent and returns curated pass/fail evidence.

Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output.

Refresh Ito-managed assets in a project and prune stray skills/commands left behind by renames or deprecations. Use when the user asks to "update Ito", "refresh Ito templates", "update repo to latest Ito", or says the project is on an older Ito. NOT for editing individual skills, authoring new templates, or shipping Ito releases.