← ClaudeAtlas

drivelisted

Drive the REAL claude binary through clawback's PTY channel at a scripted inter-turn gap schedule — the faithful load arm. Because the bytes on the wire are produced by genuine Claude Code, this is the only driver that exercises the 1h-TTL nested-cache-control rewrite (arm A2) authentically. Use for headline/moat numbers and to cross-check the HTTP replay arm (.skills/replay). Requires node-pty and a running clawback proxy.
zapgun-ai/clawback · ★ 2 · AI & Automation · score 63
Install: claude install-skill zapgun-ai/clawback
# clawback PTY-driven load driver (faithful arm) Run `benchmark/bin/drive_pty.js` from the project root. It launches the real `claude` binary inside a PTY clawback owns (reusing `src/launch_claude.js` → `ptyProcess.write()`, the same mechanism auto-continue uses) and types scripted prompts on a schedule. Data is captured by the **proxy's** `--turn-log` — start the proxy (with its turn-log) via `.skills/monitor` first, pointed at the same `--port`. ## Why this arm exists The request bytes are, by definition, exactly what Claude Code sends — including the precise `cache_control` breakpoint nesting that the 1h-TTL moat rewrites. The HTTP replay arm (`.skills/replay`) can only *approximate* that with a fixture. Agreement between the two arms is what makes a claim bulletproof; divergence is itself a finding. ## Requirements - `node-pty` installed (clawback's optional dep). Without it the driver errors out — it cannot fall back to non-PTY (it needs the master FD to inject keystrokes). - A running clawback proxy with a `--turn-log`. - The real `claude` binary on `PATH` (or `--command <path>`). A real run spends real tokens through `claude`. ## Usage ```bash # print the planned gap schedule + prompt loading, spawn nothing: node benchmark/bin/drive_pty.js --dry-run --profile L0 --turns 5 # real run at L2 (5–30 min gaps), 30 turns: node benchmark/bin/drive_pty.js --profile L2 --turns 30 \ --prompts benchmark/prompts/coding.txt --settle-sec 8 ``` ## Key options - `--pr