Skip to content
PromptAgent Governance

Production Agent Operating Files

Design and implement the complete operating-file pack and runtime contract for a specialised agent, aligning role, scope, policy, tools, memory, machine-enforced permissions, tests, runtime health, and operator evidence.

Problem
Agent behaviour files can describe permissions or capabilities that the actual runtime does not enforce, leaving documentation and execution authority out of sync.

Core outcomes

  • Bounded agent role and scope
  • Machine-readable manifest
  • Tool and permission enforcement
  • Durable memory boundaries
  • Runtime verification
  • Operator-facing status evidence

Requirements

Preconditions an agent should verify before selecting this capability.

  • TypeScript or JavaScript agent runtime or repository
  • Task orchestrator or invocation entrypoint
  • Machine-readable agent manifest
  • Tool or skill gateway
  • Durable runtime state
  • Test runner
  • Bounded agent role
  • Explicit approval boundaries

Boundaries

Published limitations that constrain safe use.

  • Markdown shapes behaviour but does not enforce permissions
  • Runtime evidence and executable enforcement outrank prose
  • Do not infer a running service from source presence
  • Contradictions between docs, config, and runtime must be reported

Catalogue source

Repository:
AyobamiH/agent-shop-products (main)
Payload path:
products/production-agent-operating-files/PROMPT.md

Price, ratings, reviews and the full prompt body are not published. Nothing on this page is inferred from data the catalogue does not contain.

Machine-readable

metadata Markdowncanonical catalogue JSONagent discovery text

Tags

  • #agent-operating-files
  • #governance
  • #tool-permissions
  • #runtime-contract
  • #memory

Related products

Selected by shared category and catalogue tags. No popularity or purchase signal exists.

  • PromptAgent Governance

    Capability-Gap Learning System

    Build a governed system that classifies why agent work is blocked, separates missing capability from missing permission, proposes the smallest justified improvement, validates it, and retries the original task without self-granting authority.

    #agent-governance#capability-gaps#permissions+2