Gsd Plan Review Convergence

B. User Prompting

When the workflow needs user input, prompt the user conversationally:

• Present options as a numbered list in your response text
• Ask the user to reply with their choice
• For multi-select, ask for comma-separated numbers

C. Tool Usage

Use these Augment tools when executing GSD workflows:

• launch-process for running commands (terminal operations)
• str-replace-editor for editing existing files
• view for reading files and listing directories
• save-file for creating new files
• grep for searching code (or use MCP servers for advanced search)
• web-search, web-fetch for web queries
• add_tasks, view_tasklist, update_tasks for task management

D. Subagent Spawning

When the workflow needs to spawn a subagent:

• Use the built-in subagent spawning capability
• Define agent prompts in .augment/agents/ directory

Flow: Agent→Skill("gsd-plan-phase") → Agent→Skill("gsd-review") → check HIGHs → Agent→Skill("gsd-plan-phase --reviews") → Agent→Skill("gsd-review") → ... → Converge or escalate

Replaces gsd-plan-phase's internal gsd-plan-checker with external AI reviewers (codex, gemini, etc.). Each step runs inside an isolated Agent that calls the corresponding existing Skill — orchestrator only does loop control.

Orchestrator role: Parse arguments, validate phase, spawn Agents for existing Skills, check HIGHs, stall detection, escalation gate.

Flags:

• --codex — Use Codex CLI as reviewer (default if no reviewer specified)
• --gemini — Use Gemini CLI as reviewer
• --claude — Use Claude CLI as reviewer (separate session)
• --opencode — Use OpenCode as reviewer
• --ollama — Use local Ollama server as reviewer (OpenAI-compatible, default host http://localhost:11434; configure model via review.models.ollama)
• --lm-studio — Use local LM Studio server as reviewer (OpenAI-compatible, default host http://localhost:1234; configure model via review.models.lm_studio)
• --llama-cpp — Use local llama.cpp server as reviewer (OpenAI-compatible, default host http://localhost:8080; configure model via review.models.llama_cpp)
• --all — Use all available CLIs and running local model servers
• --max-cycles N — Maximum replan→review cycles (default: 3)

Feature gate: This command requires workflow.plan_review_convergence=true. Enable with: gsd config-set workflow.plan_review_convergence true