Skip to content

yeaight7/agent-powerups / plugins/dev-vitals/skills/agent-runtime-patterns

agent-runtime-patterns

Verified

Use when optimizing agent runtime loops, card packs, MCP session lifecycle, tool-call count, or multi-agent orchestration patterns.

Agent Runtime Patterns

When to use

  • Optimizing a slow or over-spending agent loop (too many tool calls, high token use).
  • Designing multi-agent orchestration topology for a new workflow.
  • Managing MCP session lifecycle for experimental data-layer sessions.
  • Reducing redundant search or file-read loops.

Core Patterns

PatternUse whenAvoid when
Direct executionSingle agent, clear scope, no subagent benefitsTask genuinely requires parallel sub-agents or specialized routing
RoutingInput type determines which specialized agent to invokeAgents share context and can't be isolated
ChainingOutput of A is strict input of BAgents need to share partial context
Orchestrator-workerParallel independent subtasks with a coordinatorTasks are tightly coupled or sequential
Agents-as-toolsCallable child agent inside a parent's tool loopThe child needs user interaction

Knowledge Cards

A card is a compact, high-signal instruction block — typically 3–10 lines — for a specific operation. Cards are preferable to loading full documentation into context.

Good card: step sequence + key constraint + example invocation. Bad card: copied README sections, multiple unrelated topics in one block.

Pack cards for the current task only. Swap cards between phases rather than accumulating them.

Workflow

  1. Identify the bottleneck — measure before optimizing: count tool calls, token usage, and latency. Name the specific slow or expensive step.
  2. Choose the right pattern — use the table above. Default to direct execution; add orchestration only when simpler approaches are insufficient.
  3. Pack knowledge as cards — replace large prompt docs with targeted 5–10 line cards per operation.
  4. Bound search loops — cap retries (e.g., max 3 search attempts), normalize query construction, prefer a dedicated search subagent over inline ad-hoc loops.
  5. Model MCP sessions explicitly — for experimental sessions: track create/delete lifecycle, request _meta session IDs, handle missing-session errors without silent retries.
  6. Measure after — compare latency, tool-call count, token use, and task success rate before/after.

Safety Constraints

  • Sandbox experimental runtime changes; do not deploy to production flows without verified before/after comparison.
  • Do not add orchestration layers to compensate for unclear requirements — clarify the task first.
  • Do not persist session state containing secrets without an explicit storage policy.
  • Do not retry failed sessions silently; surface the error.

Validation / Done Criteria

  • Measurable before/after evidence: fewer tool calls, lower latency, lower token use, or higher task success.
  • Chosen orchestration pattern is named and justified.
  • Session lifecycle and cleanup behavior are documented if MCP sessions were introduced.

References

  • references/runtime-patterns.md
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 468kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall