Bash as Universal Tool¶
Design claim from jared-zoneraich: of all claude-code's tools (read, edit, grep, glob, web_fetch, todo, task, bash), bash is the one that actually does the work — the rest are optimisations around token budget, safety, and UX.
Why bash wins¶
- Universal adapter. Thousands of CLI tools already do everything an engineer does — spin up envs, run tests, scaffold files, call APIs — so the agent inherits an ecosystem for free.
- Overwhelming training data. Models are dramatically better at bash than at Rust or Zig because of corpus bias. "It's the reason models are worse at less common languages — fewer people doing it." (See claude-code's Zig weakness from mitchell-hashimoto-zed-agentic-2025.)
- Durable long-term memory via the filesystem. Agent can write Python, run it, delete it; write markdown notes and re-read them later. Filesystem-as-memory is cheaper than in-context memory and sidesteps context-compaction.
Zoneraich's forward bet¶
"I'm on the proponent of one mega tool call instead of a lot of tool calls." Counter-thesis to the hundreds-of-tool-calls camp: as models improve, shrink tools back toward bash + a few rigorous specialised calls.
Friction¶
Bash is also the main attack surface — prompt injection from web_fetch, destructive commands (team members "dropped all their local databases"), hence the heavy sandboxing/permissions layer. See claude-code architecture section.