WenyuChiou

codex-delegate

Delegates implementation-heavy or repetitive coding work (batch edits, boilerplate, multi-file refactors with clear patterns, test scaffolding) from Claude to OpenAI Codex CLI. Use when token cost outweighs judgment cost. Trigger phrases include "delegate to codex", "let codex do this", "batch refactor across files", "scaffold tests for". Avoid for architecture, security review, or root-cause debugging.

63 Updated 1 months ago

agent-acceptance-gate

Use when reconciled multi-agent output needs an evidence-based PASS, CONDITIONAL PASS, or FAIL record before authorized delivery.

agent-context-budget

Use when an agent task needs bounded context packets, checkpoint-aware compaction, a fresh-session primer, or policy-controlled child results without loading raw logs into the primary session.

agent-debate

Use when a consequential decision has genuinely competing positions that need bounded adversarial review before a human decision.

agent-output-reconciler

Use when multiple agent results must be checked for missing evidence, scope drift, contradictions, and merge conflicts before an acceptance decision.

agent-plan-act-reflect

Use when one agent must iteratively plan, act, evaluate evidence, and revise under a readable policy until acceptance, checkpoint, stop, or human escalation.

agent-shared-memory

Use when a user asks to inspect coordination memory, propose a durable decision or resolution, review pending memory proposals, or apply an explicitly approved proposal as a new append-only event.

agent-task-splitter

Use when a goal needs multiple bounded agent roles, parallel or dependent task packets, explicit scope partitions, and a provider-neutral DAG. Not for research-domain routing that owns .research, .paper, Zotero, Obsidian, or NotebookLM workflows; use research-hub-multi-ai for those.