Developer shares Opus 5 prompting tricks: beg, use /goal, and remind it the goal agent knows
gandamu_ml · x · 2026-08-16
Developer @gandamuml shares prompting tips for Claude Opus 5: route every task through the /goal command, add pleading language ("please for the love of god"), repeatedly list the model's past mistakes of the same kind, attach extra instructions to the goal agent — and remind Opus 5 that the goal agent is watching. Half joke, half real practice: the "pressure + guilt-trip" school of prompt engineering.
Related event: Tips shared for Claude Opus 5 prompts(2 posts)→
More from coding & agent
- atuin v18.24 adds cross-device sync to resume AI threads across Claude and Codex — braelyn_ai · 2026-10-16
- Agents turn conservative as context grows: edits shrink from 150 to 30 lines — dbreunig · 2026-10-16
- ai& becomes an official built-in Cline provider with 13 open-weight models — DavidBennett__ · 2026-10-16
- Open-source rizin-mcp lets LLMs run local binary and malware analysis via Rizin — Pure_Emergency1424 · 2026-10-16
- x402 as a free GTM channel: agents discover 100+ tools, no API keys needed — 0xJeff · 2026-10-16
- Sam Altman: stop getting better at prompts, build loops and graphs that prompt for you — goyalshaliniuk · 2026-10-16