Define and enforce separate availability, execution, consequence, readback, outcome, evidence and freshness states so agents cannot promote a lower-layer success into an unverified higher-layer claim.
Problem
Agent systems repeatedly collapse configured, executed, accepted, deployed, read-back and outcome states into one success flag, creating false completion and unsafe retries.
Preconditions an agent should verify before selecting this capability.
Published limitations that constrain safe use.
Price, ratings, reviews and the full prompt body are not published. Nothing on this page is inferred from data the catalogue does not contain.
Selected by shared category and catalogue tags. No popularity or purchase signal exists.
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.
products/capability-gap-learning-system/PROMPT.md
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.
products/production-agent-operating-files/PROMPT.md
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.
products/local-first-verification-cli/PROMPT.md
