Map Codebase

Map Codebase

Deep architecture report. Fans out parallel inspections across different aspects of the codebase, synthesizes their findings, and writes .turbo/codebase-map.md and .turbo/codebase-map.html. Analysis-only.

Task Tracking

At the start, use TaskCreate to create a task for each phase:

1. Scope
2. Launch inspection agents
3. Synthesize and generate markdown report
4. Generate HTML report

Step 1: Scope

If $ARGUMENTS specifies paths, use those directly (skip the question).

Otherwise, use AskUserQuestion to confirm scope:

• Entire codebase — inspect everything
• Specific paths — user provides directories or file patterns

Once scope is determined, glob for source files in the selected scope. Exclude generated and vendored directories (node_modules/, dist/, build/, vendor/, __pycache__/, .build/, DerivedData/, target/, .tox/, and others appropriate to the project).

Build a file manifest grouped by top-level source directory. This manifest is shared with all agents as a starting point. Agents may explore beyond it based on what they discover.

Step 2: Launch Inspection Agents

Before dispatching, read the project's test configuration and CI workflow to identify any test tier that resets a shared external resource between tests, such as a database, a fixed port, or a cache. Such tiers have no cross-process interlock, so agents running them concurrently wipe each other's state and return failures that look like real defects. Name any such tier to every agent as off-limits.

Emit all 7 Agent tool calls below in one assistant message. Each Agent call uses model: "opus" and no name. Wait for every agent to report before continuing. Do not begin the next step on a partial set, and do not relaunch an agent that has not yet reported. Each agent receives the scoped file manifest and its exploration brief, and its prompt directs it to treat the shared working tree and its git index as read-only — any empirical check runs in an isolated git worktree created under $TMPDIR and discarded afterward. HEAD stays where it is: read other refs with git show <ref>:<path> rather than git checkout or git switch. Give that worktree its own dependency install rather than reaching the shared tree's install by any route: removing a worktree deletes through symlinks, and a redirected suite writes into the shared install. When its own install is not possible, the check is left unrun and reported as such. Afterward the agent verifies that git worktree list no longer shows the worktree, that git status --short is clean, that HEAD is still on the branch it started on, and that the shared tree's dependency directory still resolves (a destroyed install leaves git status clean, since it is gitignored). Damage the agent cannot repair is reported with the exact repair command in place of findings.

Dimensions

Launch one agent per dimension. Each agent's prompt provides the file manifest and the exploration brief below. Agents explore adaptively: go deeper where complexity warrants it, stay high-level where things are straightforward. Findings should be concrete (reference specific files and directories) rather than generic.