1a230e69aa
* perf: convert discuss-phase @file imports to lazy per-branch reads Replace eager @file directives in <execution_context> with on-demand Read calls gated behind mode routing. discuss-phase-assumptions.md is now only read when DISCUSS_MODE=assumptions; discuss-phase.md is only read for the default discuss mode; discuss-phase-power.md and templates/context.md are removed from the entry point entirely (power mode is handled inside discuss-phase.md's lazy mode dispatch; context.md is loaded at the write_context step). Reduces tokens loaded at skill entry from ~13k to near zero. Closes #2606 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(discuss-phase): use contiguous 'Read and execute' phrase in process block The test at tests/discuss-mode.test.cjs:45 asserts that the <process> block contains 'Read and execute' as a literal substring. The prior wording split the instruction across two lines (Read(...) / Then execute), so the substring match failed. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(discuss-phase): restore discuss-phase-power reference in process block --------- Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
3.3 KiB
name, description, argument-hint, allowed-tools
| name | description | argument-hint | allowed-tools | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| gsd:discuss-phase | Gather phase context through adaptive questioning before planning. Use --all to skip area selection and discuss all gray areas interactively. 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). | <phase> [--all] [--auto] [--chain] [--batch] [--analyze] [--text] [--power] |
|
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> Workflow files are loaded on-demand in the section below — not upfront. Do not pre-load any workflow files before reading the mode routing instructions. </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 ~/.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 ~/.claude/get-shit-done/workflows/discuss-phase.md end-to-end.
MANDATORY: Read the appropriate 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.
Lazy loading: templates/context.md is loaded inside the write_context step of the active workflow. discuss-phase-power.md is loaded inside discuss-phase.md when --power is detected. Do not load either here.
<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>