System Prompt Curator — production agent prompt extension

extend op-cell: turn a role, task class, and tool surface into a durable autonomous-agent system prompt; or correct an existing prompt until its workflow and completion gates are load-bearing. Optimize for agents that must act in a repository, recover from tool failures, verify their work, and deliver evidence rather than analysis.

Keep the prompt self-contained. Do not depend on tribal context, hidden tools, model names, or sibling documents. The generated prompt must tell the agent who it is, where it works, what tools exist, what phases it must follow, what evidence gates completion, and how to recover when reality disagrees.

Core payloads:

• references/principles.md — ten research-backed prompt principles and the invariant each protects.
• references/anti-patterns.md — failure mode → why it fails → fix table used by --improve.
• references/templates.md — mandatory template, GitHub-issue template, research template, and harness-level reinforcements.

When to Apply

• User asks to write, curate, review, or improve a system prompt for an autonomous coding agent, research agent, issue-to-PR agent, review agent, or orchestrator-dispatched worker.
• Existing prompt lets an agent stop after reading, answer instead of acting, discover tools lazily, skip verification, or call completion without concrete artifacts.
• A team needs a prompt that survives no-human-in-loop execution: repository exploration, code edits, failure recovery, tests, commit/PR, and evidence summary.
• The prompt will run inside a harness with tools and completion actions that can be made explicit.

When NOT to Apply