Name: gsd:discuss-phase
Author: cachemoney

Prompt file imported from cachemoney/hls-3d (.claude/commands/gsd/discuss-phase.md). Fill in {{arguments}} before use. Copyright stays with the author.

How it works:

Load prior context (PROJECT.md, REQUIREMENTS.md, STATE.md, prior CONTEXT.md files)
Scout codebase for reusable assets and patterns
Analyze phase — skip gray areas already decided in prior phases
Present remaining gray areas — user selects which to discuss
Deep-dive each selected area until satisfied
Create CONTEXT.md with decisions that guide research and planning

Output: {phase_num}-CONTEXT.md — decisions clear enough that downstream agents can act without asking the user again

<execution_context> @/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/workflows/discuss-phase.md @/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/workflows/discuss-phase-assumptions.md @/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/workflows/discuss-phase-power.md @/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/templates/context.md </execution_context>

<runtime_note> Copilot (VS Code): Use vscode_askquestions wherever this workflow calls AskUserQuestion. They are equivalent — vscode_askquestions is the VS Code Copilot implementation of the same interactive question API. </runtime_note>

Context files are resolved in-workflow using init phase-op and roadmap/state tool calls.

If DISCUSS_MODE is "assumptions": Read and execute @/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/workflows/discuss-phase-assumptions.md end-to-end.

If DISCUSS_MODE is "discuss" (or unset, or any other value): Read and execute @/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/workflows/discuss-phase.md end-to-end.

MANDATORY: The execution_context files listed above ARE the instructions. Read the workflow file BEFORE taking any action. The objective and success_criteria sections in this command file are summaries — the workflow file contains the complete step-by-step process with all required behaviors, config checks, and interaction patterns. Do not improvise from the summary.

<success_criteria>

Prior context loaded and applied (no re-asking decided questions)
Gray areas identified through intelligent analysis
User chose which areas to discuss
Each selected area explored until satisfied
Scope creep redirected to deferred ideas
CONTEXT.md captures decisions, not vague vision
User knows next steps </success_criteria>

<objective> Extract implementation decisions that downstream agents need — researcher and planner will use CONTEXT.md to know what to investigate and what choices are locked. **How it works:** 1. Load prior context (PROJECT.md, REQUIREMENTS.md, STATE.md, prior CONTEXT.md files) 2. Scout codebase for reusable assets and patterns 3. Analyze phase — skip gray areas already decided in prior phases 4. Present remaining gray areas — user selects which to discuss 5. Deep-dive each selected area until satisfied 6. Create CONTEXT.md with decisions that guide research and planning **Output:** `{phase_num}-CONTEXT.md` — decisions clear enough that downstream agents can act without asking the user again </objective> <execution_context> @/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/workflows/discuss-phase.md @/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/workflows/discuss-phase-assumptions.md @/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/workflows/discuss-phase-power.md @/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/templates/context.md </execution_context> <runtime_note> **Copilot (VS Code):** Use `vscode_askquestions` wherever this workflow calls `AskUserQuestion`. They are equivalent — `vscode_askquestions` is the VS Code Copilot implementation of the same interactive question API. </runtime_note> <context> Phase number: {{arguments}} (required) Context files are resolved in-workflow using `init phase-op` and roadmap/state tool calls. </context> <process> **Mode routing:** ```bash DISCUSS_MODE=$(node "/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/bin/gsd-tools.cjs" config-get workflow.discuss_mode 2>/dev/null || echo "discuss") ``` If `DISCUSS_MODE` is `"assumptions"`: Read and execute @/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/workflows/discuss-phase-assumptions.md end-to-end. If `DISCUSS_MODE` is `"discuss"` (or unset, or any other value): Read and execute @/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/workflows/discuss-phase.md end-to-end. **MANDATORY:** The execution_context files listed above ARE the instructions. Read the workflow file BEFORE taking any action. The objective and success_criteria sections in this command file are summaries — the workflow file contains the complete step-by-step process with all required behaviors, config checks, and interaction patterns. Do not improvise from the summary. </process> <success_criteria> - Prior context loaded and applied (no re-asking decided questions) - Gray areas identified through intelligent analysis - User chose which areas to discuss - Each selected area explored until satisfied - Scope creep redirected to deferred ideas - CONTEXT.md captures decisions, not vague vision - User knows next steps </success_criteria>

{ "prompt": "<objective>\nExtract implementation decisions that downstream agents need — researcher and planner will use CONTEXT.md to know what to investigate and what choices are locked.\n\n**How it works:**\n1. Load prior context (PROJECT.md, REQUIREMENTS.md, STATE.md, prior CONTEXT.md files)\n2. Scout codebase for reusable assets and patterns\n3. Analyze phase — skip gray areas already decided in prior phases\n4. Present remaining gray areas — user selects which to discuss\n5. Deep-dive each selected area until satisfied\n6. Create CONTEXT.md with decisions that guide research and planning\n\n**Output:** `{phase_num}-CONTEXT.md` — decisions clear enough that downstream agents can act without asking the user again\n</objective>\n\n<execution_context>\n@/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/workflows/discuss-phase.md\n@/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/workflows/discuss-phase-assumptions.md\n@/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/workflows/discuss-phase-power.md\n@/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/templates/context.md\n</execution_context>\n\n<runtime_note>\n**Copilot (VS Code):** Use `vscode_askquestions` wherever this workflow calls `AskUserQuestion`. They are equivalent — `vscode_askquestions` is the VS Code Copilot implementation of the same interactive question API.\n</runtime_note>\n\n<context>\nPhase number: {{arguments}} (required)\n\nContext files are resolved in-workflow using `init phase-op` and roadmap/state tool calls.\n</context>\n\n<process>\n**Mode routing:**\n```bash\nDISCUSS_MODE=$(node \"/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/bin/gsd-tools.cjs\" config-get workflow.discuss_mode 2>/dev/null || echo \"discuss\")\n```\n\nIf `DISCUSS_MODE` is `\"assumptions\"`: Read and execute @/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/workflows/discuss-phase-assumptions.md end-to-end.\n\nIf `DISCUSS_MODE` is `\"discuss\"` (or unset, or any other value): Read and execute @/home/mezmo/Work/projects/hls-3d/.claude/get-shit-done/workflows/discuss-phase.md end-to-end.\n\n**MANDATORY:** The execution_context files listed above ARE the instructions. Read the workflow file BEFORE taking any action. The objective and success_criteria sections in this command file are summaries — the workflow file contains the complete step-by-step process with all required behaviors, config checks, and interaction patterns. Do not improvise from the summary.\n</process>\n\n<success_criteria>\n- Prior context loaded and applied (no re-asking decided questions)\n- Gray areas identified through intelligent analysis\n- User chose which areas to discuss\n- Each selected area explored until satisfied\n- Scope creep redirected to deferred ideas\n- CONTEXT.md captures decisions, not vague vision\n- User knows next steps\n</success_criteria>", "variables": [ "arguments" ], "notes": "Gather phase context through adaptive questioning before planning. Use --auto to skip interactive questions (Claude picks recommended defaults). Use --chain for interactive discuss followed by automatic plan+execute. Use --power for bulk question generation into a file-based UI (answer at your own pace). Tools: Read, Write, Bash, Glob, Grep, AskUserQuestion, Task, mcp__context7__resolve-library-id, mcp__context7__query-docs. Arguments: <phase> [--auto] [--chain] [--batch] [--analyze] [--text] [--power].", "metadata": { "source": { "provider": "github-claude-commands", "repository": "https://github.com/cachemoney/hls-3d", "path": ".claude/commands/gsd/discuss-phase.md", "ref": "9d27cc0a559f6be3fd00326d13c325672187161f", "url": "https://github.com/cachemoney/hls-3d/blob/9d27cc0a559f6be3fd00326d13c325672187161f/.claude/commands/gsd/discuss-phase.md", "key": "cachemoney/hls-3d/.claude/commands/gsd/discuss-phase.md" } } }

gsd:discuss-phase

About

Use it

Manifest

Reviews