Strategies that scale to 100k+ LOC. Scoping, parallel sessions, lockfile discipline, and the comparison data on which agents cope best.
In a 400k-line workspace, an unscoped agent burns half its context discovering packages it will never touch — then edits one it shouldn't. Run the agent from the package directory, deny writes outside it, and hand it the workspace-level commands it still needs.
The root file that keeps five agents from treating 40 packages as one big sandbox: affected-only commands, module boundaries with an owner column, and a hard rule about generated code.
We tested both on a 200k+ LOC codebase. Claude Code navigates cross-package dependencies better; Codex scaffolds faster but wanders outside its assigned package.
Run three or four agents against the same repo without them stomping each other's changes. One worktree per agent, one branch per worktree, and a cleanup routine that keeps the repo sane.
Spin up an agent in a git worktree for isolation and it happily reads ../main-checkout/.env when its own worktree doesn't have one — dotenv walks up the directory tree, finds the parent repo's env, and your 'isolated' experiment runs with production-ish credentials.
Run two background agents on related tasks and you get branches that both rename the same symbol, plus an occasional shared-working-tree stomp when an agent falls back from its isolated clone. Merging their PRs is a coin flip of conflicts.
Agents love 'fixing' installs by regenerating the lockfile, and every regeneration is a 3,000-line diff nobody reviews. Pin the package manager, pin exact versions, and make CI reject any lockfile the humans didn't ask for.