Skip to content
PromptProduction Operations

Read-Only Production System Reconnaissance

Map a live software system without mutating source, services, schedules, databases, credentials, providers, or runtime state, while reconciling documentation against observed runtime truth.

Problem
A confident but incorrect production inventory can be more dangerous than an incomplete one, especially when stale documentation is treated as authoritative.

Core outcomes

  • Zero-write production inventory
  • Process, socket, service, scheduler, repository, and datastore discovery
  • Secret-safe configuration shape discovery
  • Contradiction reconciliation
  • Evidence-backed risk and portability report

Requirements

Preconditions an agent should verify before selecting this capability.

  • Read access to host/runtime
  • Read access to relevant repositories/configuration
  • Bounded shell inspection
  • Read-only service/process/socket/container/database queries
  • Secure report destination
  • Secret and private-data boundaries
  • Defined operator scope

Boundaries

Published limitations that constrain safe use.

  • No repair, restart, reload, install, update, migrate, delete, publish, rotate, or reconcile
  • Runtime and provider evidence outrank documentation
  • Unavailable or unverified components cannot be reported healthy
  • Preserve contradictions rather than editing them away

Catalogue source

Repository:
AyobamiH/agent-shop-products (main)
Payload path:
products/read-only-production-reconnaissance/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

  • #reconnaissance
  • #production
  • #read-only
  • #runtime-truth
  • #inventory

Related products

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

  • PromptDeveloper Tooling

    Local-First Verification CLI

    Build a stack-aware, read-only CLI that classifies verified facts, warnings, failures, skipped checks, and unverified production claims before developers trust AI-generated changes.

    #cli#verification#read-only+2