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
Designed for power users who want to parallelize work across phases from one terminal: discuss a phase while another plans or executes in the background.
Creates/Updates:
- No files created directly — dispatches to existing GSD commands via Skill() and background Task agents.
- Reads
.planning/STATE.md, .planning/ROADMAP.md, phase directories for status.
After: User exits when done managing, or all phases complete and milestone lifecycle is suggested.
Project context, phase list, dependencies, and recommendations are resolved inside the workflow using gsd-tools.cjs init manager. No upfront context loading needed.
1---2name: "gsd-manager"3description: "Interactive command center for managing multiple phases from one terminal"4metadata:5 short-description: "Interactive command center for managing multiple phases from one terminal"6---78<codex_skill_adapter>9## A. Skill Invocation10- This skill is invoked by mentioning `$gsd-manager`.11- Treat all user text after `$gsd-manager` 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>49Single-terminal command center for managing a milestone. Shows a dashboard of all phases with visual status indicators, recommends optimal next actions, and dispatches work — discuss runs inline, plan/execute run as background agents.5051Designed for power users who want to parallelize work across phases from one terminal: discuss a phase while another plans or executes in the background.5253**Creates/Updates:**54- No files created directly — dispatches to existing GSD commands via Skill() and background Task agents.55- Reads `.planning/STATE.md`, `.planning/ROADMAP.md`, phase directories for status.5657**After:** User exits when done managing, or all phases complete and milestone lifecycle is suggested.58</objective>5960<execution_context>61@/Users/richardhightower/clients/spillwave/src/agent-brain/.codex/get-shit-done/workflows/manager.md62@/Users/richardhightower/clients/spillwave/src/agent-brain/.codex/get-shit-done/references/ui-brand.md63</execution_context>6465<context>66No arguments required. Requires an active milestone with ROADMAP.md and STATE.md.6768Project context, phase list, dependencies, and recommendations are resolved inside the workflow using `gsd-tools.cjs init manager`. No upfront context loading needed.69</context>7071<process>72Execute the manager workflow from @/Users/richardhightower/clients/spillwave/src/agent-brain/.codex/get-shit-done/workflows/manager.md end-to-end.73Maintain the dashboard refresh loop until the user exits or all phases complete.74</process>