Battle-tested prompt patterns for production AI agents. Covers consumer-first design, deletion test, cascading validation, advisory mode tiers, proof-of-work enforcement, heartbeat protocol, contradiction detection, WAL protocol, rule escalation ladder, and cross-validation patterns.
SkillScore43Maintained
Automatic
◆AI Engineer pack
Last verified 7/26/2026
What it changes
Passed 10 of 23 test cases with the skill, and 2 of 23 without it.
Without skill9%
With skill43%
8 fixed2 passed either way13 still failing0 broke
Pass-rate lift
+35 pp
Tokens
+256%
Agent turns
0%
Response time
-6%
Model gemini-3.6-flashMeasured 7/26/2026v110 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
What's inside
The instructions your model reads when the skill loads.
SKILL.md766 linessingle file
Agent Prompt Patterns
Battle-tested patterns for agents that ship, not agents that demo.
If your agent works in a live-fire notebook but breaks in production, you have a demo, not an agent.
When to Use
Designing a new agent's behavioral rules and operating manual
An agent is hallucinating completions, skipping steps, or claiming work it didn't do
Building multi-agent pipelines where output quality compounds (or collapses)
Setting up human-in-the-loop approval tiers for different risk levels
Enforcing reliability in automated workflows (cron jobs, scheduled tasks, pipelines)
Writing AGENTS.md or operating manuals for production agent workspaces
Debugging why an agent keeps violating rules you've already stated
Evaluating whether an agent should exist at all (deletion test)
Building harnesses that make autonomy safe and useful
When NOT to Use
One-shot prompts with no agent persistence — these patterns assume continuity
Pure chatbot / conversational UX with no action-taking capability
Academic prompt engineering research — these are production patterns, not benchmarks
Agents with no filesystem, no tool access, and no side effects — nothing to harness
You're still in the "make it work at all" phase — get basic functionality first, then harden
1. Consumer-First Design
Principle: Every agent output must have a named consumer. If nobody uses the output, the agent shouldn't exist.
This is the most important pattern because it kills bloat before it starts. Agents proliferate. Each one feels useful when you build it. Six months later you have 14 agents and can't remember what half of them do.
The Deletion Test
Ask: If I delete this agent, which other agent's work breaks?
If the answer is "nothing" or "I'm not sure," the agent is a vanity project.