B. AskUserQuestion → request_user_input Mapping
GSD workflows use AskUserQuestion (Claude Code syntax). Translate to Codex request_user_input:
Parameter mapping:
header → header
question → question
- Options formatted as
"Label" — description → {label: "Label", description: "description"}
- Generate
id from header: lowercase, replace spaces with underscores
Batched calls:
AskUserQuestion([q1, q2]) → single request_user_input with multiple entries in questions[]
Multi-select workaround:
- Codex has no
multiSelect. Use sequential single-selects, or present a numbered freeform list asking the user to enter comma-separated numbers.
Execute mode fallback:
- When
request_user_input is rejected (Execute mode), present a plain-text numbered list and pick a reasonable default.
C. Task() → spawn_agent Mapping
GSD workflows use Task(...) (Claude Code syntax). Translate to Codex collaboration tools:
Direct mapping:
Task(subagent_type="X", prompt="Y") → spawn_agent(agent_type="X", message="Y")
Task(model="...") → omit (Codex uses per-role config, not inline model selection)
fork_context: false by default — GSD agents load their own context via <files_to_read> blocks
Parallel fan-out:
- Spawn multiple agents → collect agent IDs →
wait(ids) for all to complete
Result parsing:
- Look for structured markers in agent output:
CHECKPOINT, PLAN COMPLETE, SUMMARY, etc.
close_agent(id) after collecting results from each agent
Default flow: Research (if needed) → Plan → Verify → Done
Orchestrator role: Parse arguments, validate phase, research domain (unless skipped), spawn gsd-planner, verify with gsd-plan-checker, iterate until pass or max iterations, present results.
Flags:
--research — Force re-research even if RESEARCH.md exists
--skip-research — Skip research, go straight to planning
--gaps — Gap closure mode (reads VERIFICATION.md, skips research)
--skip-verify — Skip verification loop
--prd <file> — Use a PRD/acceptance criteria file instead of discuss-phase. Parses requirements into CONTEXT.md automatically. Skips discuss-phase entirely.
--reviews — Replan incorporating cross-AI review feedback from REVIEWS.md (produced by $gsd-review)
--text — Use plain-text numbered lists instead of TUI menus (required for /rc remote sessions)
Normalize phase input in step 2 before any directory lookups.
1---2name: gsd-plan-phase3description: Create detailed phase plan (PLAN.md) with verification loop4---56<codex_skill_adapter>7## A. Skill Invocation8- This skill is invoked by mentioning `$gsd-plan-phase`.9- Treat all user text after `$gsd-plan-phase` as `{{GSD_ARGS}}`.10- If no arguments are present, treat `{{GSD_ARGS}}` as empty.1112## B. AskUserQuestion → request_user_input Mapping13GSD workflows use `AskUserQuestion` (Claude Code syntax). Translate to Codex `request_user_input`:1415Parameter mapping:16- `header` → `header`17- `question` → `question`18- Options formatted as `"Label" — description` → `{label: "Label", description: "description"}`19- Generate `id` from header: lowercase, replace spaces with underscores2021Batched calls:22- `AskUserQuestion([q1, q2])` → single `request_user_input` with multiple entries in `questions[]`2324Multi-select workaround:25- Codex has no `multiSelect`. Use sequential single-selects, or present a numbered freeform list asking the user to enter comma-separated numbers.2627Execute mode fallback:28- When `request_user_input` is rejected (Execute mode), present a plain-text numbered list and pick a reasonable default.2930## C. Task() → spawn_agent Mapping31GSD workflows use `Task(...)` (Claude Code syntax). Translate to Codex collaboration tools:3233Direct mapping:34- `Task(subagent_type="X", prompt="Y")` → `spawn_agent(agent_type="X", message="Y")`35- `Task(model="...")` → omit (Codex uses per-role config, not inline model selection)36- `fork_context: false` by default — GSD agents load their own context via `<files_to_read>` blocks3738Parallel fan-out:39- Spawn multiple agents → collect agent IDs → `wait(ids)` for all to complete4041Result parsing:42- Look for structured markers in agent output: `CHECKPOINT`, `PLAN COMPLETE`, `SUMMARY`, etc.43- `close_agent(id)` after collecting results from each agent44</codex_skill_adapter>4546<objective>47Create executable phase prompts (PLAN.md files) for a roadmap phase with integrated research and verification.4849**Default flow:** Research (if needed) → Plan → Verify → Done5051**Orchestrator role:** Parse arguments, validate phase, research domain (unless skipped), spawn gsd-planner, verify with gsd-plan-checker, iterate until pass or max iterations, present results.52</objective>5354<execution_context>55@/Users/richardhightower/clients/spillwave/src/agent-brain/.codex/get-shit-done/workflows/plan-phase.md56@/Users/richardhightower/clients/spillwave/src/agent-brain/.codex/get-shit-done/references/ui-brand.md57</execution_context>5859<context>60Phase number: {{GSD_ARGS}} (optional — auto-detects next unplanned phase if omitted)6162**Flags:**63- `--research` — Force re-research even if RESEARCH.md exists64- `--skip-research` — Skip research, go straight to planning65- `--gaps` — Gap closure mode (reads VERIFICATION.md, skips research)66- `--skip-verify` — Skip verification loop67- `--prd <file>` — Use a PRD/acceptance criteria file instead of discuss-phase. Parses requirements into CONTEXT.md automatically. Skips discuss-phase entirely.68- `--reviews` — Replan incorporating cross-AI review feedback from REVIEWS.md (produced by `$gsd-review`)69- `--text` — Use plain-text numbered lists instead of TUI menus (required for `/rc` remote sessions)7071Normalize phase input in step 2 before any directory lookups.72</context>7374<process>75Execute the plan-phase workflow from @/Users/richardhightower/clients/spillwave/src/agent-brain/.codex/get-shit-done/workflows/plan-phase.md end-to-end.76Preserve all workflow gates (validation, research, planning, verification loop, routing).77</process>