AGENTKIT/WORKS
AgentKit Works

PACK · TRIPWIRE TIER

Prompt Ops: 150 Production Prompts

The prompts that survive contact with real codebases.

PRICE$29$19

30-DAY MONEY-BACK GUARANTEE

150 prompts refined across hundreds of real agent sessions — debugging, refactoring, code review, spec writing, incident response, and research. Every prompt annotated with when to use it, what to expect, and the failure modes to watch for. No 'act as a world-class expert' filler.

$ tree prompt-ops-150/✓ actual contents
prompt-ops/
├── README.md · LICENSE
├── CHAINING.md          ← 6 pipeline patterns
├── prompts.json         ← whole library, machine-readable
└── prompts/
    ├── 01-debugging.md          (17)
    ├── 02-code-review.md        (17)
    ├── 03-refactoring.md        (17)
    ├── 04-testing.md            (17)
    └── … 5 more categories      (82)

WHY IT'S DIFFERENT

  • Each prompt tested on real production codebases
  • Failure-mode notes: when a prompt will mislead the model
  • Organized by job: debug, review, refactor, research, write

QUESTIONS, ANSWERED

Which models do these target?+

Written for Claude-class frontier models but deliberately model-agnostic — the annotations explain the intent so you can adapt them anywhere.

How do updates work?+

Buy once, keep forever. New prompts and revisions ship to the same download link — you'll get an email when a version drops.