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 $gsd-review)
--text — Use plain-text numbered lists instead of TUI menus (required for /rc remote sessions)
Normalize phase input in step 2 before any directory lookups.
1---2name: "gsd-plan-phase"3description: "Create detailed phase plan (PLAN.md) with verification loop"4metadata:5 short-description: "Create detailed phase plan (PLAN.md) with verification loop"6---78<codex_skill_adapter>9## A. Skill Invocation10- This skill is invoked by mentioning `$gsd-plan-phase`.11- Treat all user text after `$gsd-plan-phase` as `{{GSD_ARGS}}`.12- If no arguments are present, treat `{{GSD_ARGS}}` as empty.1314## B. AskUserQuestion → request_user_input Mapping15GSD workflows use `AskUserQuestion` (Claude Code syntax). Translate to Codex `request_user_input`:1617Parameter mapping:18- `header` → `header`19- `question` → `question`20- Options formatted as `"Label" — description` → `{label: "Label", description: "description"}`21- Generate `id` from header: lowercase, replace spaces with underscores2223Batched calls:24- `AskUserQuestion([q1, q2])` → single `request_user_input` with multiple entries in `questions[]`2526Multi-select workaround:27- Codex has no `multiSelect`. Use sequential single-selects, or present a numbered freeform list asking the user to enter comma-separated numbers.2829Execute mode fallback:30- When `request_user_input` is rejected (Execute mode), present a plain-text numbered list and pick a reasonable default.3132## C. Task() → spawn_agent Mapping33GSD workflows use `Task(...)` (Claude Code syntax). Translate to Codex collaboration tools:3435Direct mapping:36- `Task(subagent_type="X", prompt="Y")` → `spawn_agent(agent_type="X", message="Y")`37- `Task(model="...")` → omit (Codex uses per-role config, not inline model selection)38- `fork_context: false` by default — GSD agents load their own context via `<files_to_read>` blocks3940Parallel fan-out:41- Spawn multiple agents → collect agent IDs → `wait(ids)` for all to complete4243Result parsing:44- Look for structured markers in agent output: `CHECKPOINT`, `PLAN COMPLETE`, `SUMMARY`, etc.45- `close_agent(id)` after collecting results from each agent46</codex_skill_adapter>4748<objective>49Create executable phase prompts (PLAN.md files) for a roadmap phase with integrated research and verification.5051**Default flow:** Research (if needed) → Plan → Verify → Done5253**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.54</objective>5556<execution_context>57@/Users/richardhightower/clients/spillwave/src/agent-brain/.codex/get-shit-done/workflows/plan-phase.md58@/Users/richardhightower/clients/spillwave/src/agent-brain/.codex/get-shit-done/references/ui-brand.md59</execution_context>6061<context>62Phase number: {{GSD_ARGS}} (optional — auto-detects next unplanned phase if omitted)6364**Flags:**65- `--research` — Force re-research even if RESEARCH.md exists66- `--skip-research` — Skip research, go straight to planning67- `--gaps` — Gap closure mode (reads VERIFICATION.md, skips research)68- `--skip-verify` — Skip verification loop69- `--prd <file>` — Use a PRD/acceptance criteria file instead of discuss-phase. Parses requirements into CONTEXT.md automatically. Skips discuss-phase entirely.70- `--reviews` — Replan incorporating cross-AI review feedback from REVIEWS.md (produced by `$gsd-review`)71- `--text` — Use plain-text numbered lists instead of TUI menus (required for `/rc` remote sessions)7273Normalize phase input in step 2 before any directory lookups.74</context>7576<process>77Execute the plan-phase workflow from @/Users/richardhightower/clients/spillwave/src/agent-brain/.codex/get-shit-done/workflows/plan-phase.md end-to-end.78Preserve all workflow gates (validation, research, planning, verification loop, routing).79</process>