Prompt LibraryAgents
Agent Context Injection & Memory Loading Prompt
Decide what to load into context at each agent step.
The prompt
At the current agent step, decide what to inject into the context window from these sources: long-term memory, retrieved docs, prior tool outputs, user instructions.
For each source, state whether to include it now, defer it, or drop it — with a one-line reason.
Constraint: total injected tokens must stay under {{budget}}.
Current step: {{step}}
Available sources:
{{sources}}Replace the {{fields}} with your own context and tighten the rules to match your domain.
More Agents prompts
AI Agent Memory Policy Design Prompt
Decide what an agent should remember across sessions and for how long.
Multi-Agent Shared Scratchpad Protocol Prompt
Define how cooperating agents read and write shared memory safely.
Agent Replanning & Error Recovery Prompt
Decide when an agent should replan vs. retry vs. escalate.
