gsd-map-codebase

name	gsd-map-codebase
description	Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents
metadata	{"short-description":"Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents"}

<codex_skill_adapter>

A. Skill Invocation

• This skill is invoked by mentioning $gsd-map-codebase.
• Treat all user text after $gsd-map-codebase as {{GSD_ARGS}}.
• If no arguments are present, treat {{GSD_ARGS}} as empty.

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 or unavailable, activate TEXT_MODE: append --text to {{GSD_ARGS}} so the workflow's built-in text-mode branching takes over. Present every AskUserQuestion call as a plain-text numbered list, then stop and wait for the user's reply. Do NOT pick a default and continue (#3018 / #3808).
• You may only proceed without a user answer when one of these is true: (a) the invocation included an explicit non-interactive flag (--auto or --all), (b) the user has explicitly approved a specific default for this question, or (c) the workflow's documented contract says defaults are safe (e.g. autonomous lifecycle paths).
• Do NOT write workflow artifacts (CONTEXT.md, DISCUSSION-LOG.md, PLAN.md, checkpoint files) until the user has answered the plain-text questions or one of (a)-(c) above applies. Surfacing the questions and waiting is the correct response — silently defaulting and writing artifacts is the #3018 failure mode.

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")
• Agent(subagent_type="X", prompt="Y") → spawn_agent(agent_type="X", message="Y")
• Task(model="...") → omit. spawn_agent has no inline model parameter; GSD embeds the resolved per-agent model directly into each agent's .toml at install time so model_overrides from .planning/config.json and ~/.gsd/defaults.json are honored automatically by Codex's agent router.
• Resolved reasoning_effort="low|medium|high|xhigh" (xhigh is a GSD/Codex tier, not a generic runtime enum) → pass reasoning_effort to spawn_agent when the runtime/tool supports it. Omit missing, empty, inherited, or unsupported values; do not invent one-off effort literals in workflow prose.
• fork_context: false by default — GSD agents load their own context via <files_to_read> blocks
• Task(isolation="worktree") / Agent(isolation="worktree") → no direct Codex mapping. Codex spawn_agent does not create or bind a git worktree automatically. Workflows that require this isolation must fail closed or use an explicit manual worktree protocol before spawning (#3360).

Spawn restriction:

• Codex restricts spawn_agent to cases where the user has explicitly requested sub-agents. When automatic spawning is not permitted, do the work inline in the current agent rather than attempting to force a spawn.
• In some Codex sessions, multi-agent tooling can be deferred. If spawn_agent is not currently visible, discover tools first via tool_search before defaulting to inline execution.

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 </codex_skill_adapter>

Analyze existing codebase using parallel gsd-codebase-mapper agents to produce structured codebase documents.

Each mapper agent explores a focus area and writes documents directly to .planning/codebase/. The orchestrator only receives confirmations, keeping context usage minimal.

Output: .planning/codebase/ folder with 7 structured documents about the codebase state.

<execution_context> @D:/Projects/pjmagee/multi-stream-viewer/.codex/gsd-core/workflows/map-codebase.md </execution_context>

- **--fast**: Lightweight scan mode — spawns one mapper agent instead of four. Accepts an optional `--focus` value: `tech`, `arch`, `quality`, `concerns`, or `tech+arch` (default). Faster and lower-context than the full map. - **--query**: Codebase intelligence query mode. Sub-commands: `query `, `status`, `diff`, `refresh`. Requires intel to be enabled in config (`intel.enabled: true`). Runs inline for query/status/diff; spawns an agent for refresh. - **(no flag)**: Full parallel map — spawns 4 mapper agents to produce all 7 codebase documents. Arguments: {{GSD_ARGS}}

Parse the first token of {{GSD_ARGS}}:

• If it is --fast: strip the flag, run the scan workflow (passing remaining args including optional --focus).
• If it is --query: strip the flag, run the intel workflow (passing remaining args as the subcommand).
• Otherwise: pass all of {{GSD_ARGS}} as focus area to the map-codebase workflow.

Load project state if exists: Check for .planning/STATE.md - loads context if project already initialized

This command can run:

• Before $gsd-new-project (brownfield codebases) - creates codebase map first
• After $gsd-new-project (greenfield codebases) - updates codebase map as code evolves
• Anytime to refresh codebase understanding

<when_to_use> Use map-codebase for:

• Brownfield projects before initialization (understand existing code first)
• Refreshing codebase map after significant changes
• Onboarding to an unfamiliar codebase
• Before major refactoring (understand current state)
• When STATE.md references outdated codebase info

Skip map-codebase for:

• Greenfield projects with no code yet (nothing to map)
• Trivial codebases (<5 files) </when_to_use>

1. Check if .planning/codebase/ already exists (offer to refresh or skip) 2. Create .planning/codebase/ directory structure 3. Spawn 4 parallel gsd-codebase-mapper agents: - Agent 1: tech focus → writes STACK.md, INTEGRATIONS.md - Agent 2: arch focus → writes ARCHITECTURE.md, STRUCTURE.md - Agent 3: quality focus → writes CONVENTIONS.md, TESTING.md - Agent 4: concerns focus → writes CONCERNS.md 4. Wait for agents to complete, collect confirmations (NOT document contents) 5. Verify all 7 documents exist with line counts 6. Commit codebase map 7. Offer next steps (typically: $gsd-new-project or $gsd-plan-phase)

<success_criteria>

• .planning/codebase/ directory created
• All 7 codebase documents written by mapper agents
• Documents follow template structure
• Parallel agents completed without errors
• User knows next steps </success_criteria>