Max out Claude thinking and ultracode on every prompt, says dev
curious_vii · x · 2026-11-05
The author explains they turn thinking all the way up and trigger ultracode on every Claude prompt, arguing it's always worth it once you've done the work of knowing what matters. Quoting a workplace heuristic—be the person who requires no follow-up—they frame the payoff as autonomy: maximum thinking avoids the back-and-forth cost of clarifications and corrections.
More from coding & agent
- Remote MCP: managing your devices remotely via the MCP protocol — Latter-Storage9610 · 2026-11-05
- MCP over HTTP: validating OAuth tokens isn't enough—check the audience claim — alvelda · 2026-11-05
- Short RL phase on GLM 5.3 Flash costs $372 vs $1,894 for notes, breaks even in 8.7 days — teortaxesTex · 2026-11-05
- Vercel Security Review finds 6,817 vulnerabilities in 24 hours, agent patches 1,411 — cramforce · 2026-11-05
- Sentry CEO runs a coding agent task for 3 hours mostly hands-off — zeeg · 2026-11-05
- One Claude Code task burned 238M tokens and $120 across 8 subagents, new usage screenshot shows — zeeg · 2026-11-05